As On Am Program

ASONAM 2011
2011 International Conference on Advances in Social Networks Analysis and Mining Kaohsiung, Taiwan / July 25-27, 2011
Conference Program
Jointly with The First Workshop on Social Network Analysis in Applications (SNAA 2011) Cyberpsychological Analysis of Social Network Sites and User Behavior (CASNSUB) The 3rd International Workshop on Mining Social Networks for Decision Support (MSNDS 2011) Workshop on Mobile Social Network 2011 (MSN 2011) The 1st International Workshop on Cloud Computing in Social Networks (CCSN 2011)
Conference Sponsors
ASONAM 2011
Academic Sponsors
National University of Kaohsiung, Taiwan National Science Council, Taiwan Ministry of Education, Taiwan Web Intelligence Consortium Taiwan Center State University of New York at Stony Brook, USA University of Southern Denmark, Denmark University of Calgary, Canada Hellenic American University, Greece Global University, Lebanon

SolventoSOFT
Industrial Sponsors
WebGenie
Kaohsiung City Government
Meet Taiwan
Bureau of Foreign Trade
Springer
In cooperation with
IEEE Computer Society
Technically supported by
&
IEEE Systems, Man, Cybernetics Society
ACM Special Interest Group on Computer Human Interaction ACM Special Interest Group on Hypertext, Hypermedia and the Web IEEE Technical Committee on Awareness Computing IEEE Technical Committee on Data Engineering IEEE Technical Committee on Granular Computing
Table of Contents
ASONAM 2011 Conference Sponsors ......................................................................................................... 1 Table of Contents .............................................................................................................. 4 Advisory Committee ..........................................................................................................5 Organizing Committee .................................................................................................... 6 Program Committee ......................................................................................................... 8 External Reviewers ........................................................................................................... 11 A Message from the General Chairs .............................................................................. 12 A Message from the Program Chairs .............................................................................13 Conference Program At a Glance................................................................................... 14 Keynote Speakers ............................................................................................................. 17 Conference Program....................................................................................................... 26 Conference Abstracts ...................................................................................................... 35 Conference Posters .......................................................................................................... 77 Conference Venue ............................................................................................................82 Conference Room Plan .................................................................................................. 84
Advisory Committee
ASONAM 2011
Frank Hsu, Fordham University, USA Been-Chien Chien, National University of Tainan, Taiwan Shie-Jue Lee, National Sun Yat-Sen University, Taiwan Tsau-Young Lin, San Jose State University, USA Wen-Yang Lin, National University of Kaohsiung, Taiwan Ngoc-Thanh Nguyen, Wroclaw University of Technology, Poland Ted Teng, State University of New York at Stony Brook, USA Shusaku Tsumoto, Shimane University, Japan Von-Wun Soo, National Tsing Hua University, Taiwan
Organizing Committee
ASONAM 2011
Honorary General Chairs
Ken Barker, University of Calgary Ing-Chung Huang, National University of Kaohsiung Per Michael Johansen, University of Southern Denmark Leonidas-Phoebus Koskos, Hellenic American University Abdul Qadeer Khan Rajput, Mehran University of Engineering and
Technology
General Chairs
Tzung-Pei Hong, National University of Kaohsiung Leon Shyue-Liang Wang, National University of Kaohsiung Uffe Kock Wiil, University of Southern Denmark
Program Chairs
Reda Alhajj, University of Calgary Nasrullah Memon, University of Southern Denmark I-Hsien Ting, National University of Kaohsiung
Publicity Chairs
Malek Haroud, Global University Ying-Feng Kuo, National University of Kaohsiung Tsau-Young Lin, San Jose State University Tansel zyer, TOBB Economics and Technology University Jon Rokne, University of Calgary Chien-Hsing Wu, National University of Kaohsiung
Publications Chairs
Panagiotis Karampelas, Hellenic American University Yu-Hui Tao, National University of Kaohsiung
Local Arrangement Chairs

Chian-Hsueng Chao Han-Wei Hsiao Chin-Fu Kuo Hsing-Tzu Lin Shing-Tai Pan
National University of Kaohsiung
Workshop / Special Session Chairs

Yingzi Jin, University of Tokyo Kai Wang, National University of Kaohsiung Shu-Chen Yang, National University of Kaohsiung
Web Chair
Hsin-Chang Yang, National University of Kaohsiung
Program Committee
ASONAM 2011 Ajith Abraham, Norwegian University of Science and Technology, Norway Nitin Agarwal, University of Arkansas at Little Rock, USA Harith Alani, University of Southampton, UK Ira Assent, Aalborg University, Denmark Guido Barbian, Unversity of Lneburg, Germany Kanishka Bhaduri, NASA, USA Marenglen Biba, University of New York Tirana, Albania Francesco Bonchi, Yahoo! Research Barcelona, Spain Dan Braha, New England Complex Systems Institute, USA Bin Cao, The Hong Kong University of Science and Technology, China Andre Carvalho, Universidade de Sao Paulo, Brazil Chien-Chung Chan, University of Akron, USA Nitesh V. Chawla, University of Notre Dame, USA Richard Chbeir, LE2I-CNRS, France Li Chen, Hong Kong Baptist University, HK Yunwei Chen, National Science Library, Chinese Academy of Sciences James Cheng, Nanyang Technological University, Singapore Yun Chi, NEC Laboratories America, USA Been-Chian Chien, National Tainan University, Taiwan Tung-Hsiang Chou, National Kaohsiung First University of Science and Technology Munmun De Choudhury, Arizona State University, Tempe, USA Gao Cong, Aalborg University, Denmark Ioanna Constantiou, Copenhagen Business School, Denmark Diane Cook, Washington State University, USA Xiaohui Cui, Oak Ridge National Laboratory, USA Alfredo Cuzzocrea, University of Calabria, Italy Min-Yuh Day, National Taiwan University, Taiwan Petra Deger, University of Regensburg, Germany Jana Diesner, Carnegie Mellon University, USA Ying Ding, Indiana University, USA Carlotta Domeniconi, George Mason University, USA Artur Dubrawski, Carnegie Mellon University, USA Schahram Dustdar, Technical University Wien, Austria Yuval Elovici, Ben-Gurion University of the Negev, Isreal Behrouz Far, University of Calgary, Canada Michael Farrugia, University College Dublin, Ireland Terrill Frantz, Carnegie Mellon University, USA Matjaz Gams, Jozef Stefan Institute, Slovenia Minos Garofalakis, Technical University of Crete, Greece Paolo Garza, Politecnico di Torino, Italy Amol Ghoting, IBM T. J. Watson Research, USA Uwe Glaesser, Simon Fraser University, Canada Tyrone Grandison, IBM Almaden Research Center, USA William Grosky, University of Michigan, USA Fabrice Guillet, Nantes University, France Jiawei Han, University of Illinois at Urbana-Champaign, USA
Sangki Steve Han, KAIST, Korea Hoang Huu Hanh, HUE University, Vietnam
Choochart Haruechaiyasak, National Electronics and Computer Technology Center, Thailand
Dominique Haughton, Bently University, USA Conor Hayes, Digital Enterprise Research Institute, Ireland Nicola Henze, University of Hannover, Germany David L. Hicks, Aalborg University, Denmark Erick Ho, Oriental Institute of Technology, Taiwan Hui-Huang Hsu, Tamkang University, Taiwan Weidong Tony Huang, CSIRO ICT Center, Australia Yun Huang, Northwestern University, USA Yuan-chu Hwang, National United University, Taiwan Ruoming Jin, Kent State University, USA Jason J. Jung, Yeungnam University, Korea Mehmed Kantardzic, University of Louisville, USA Panagiotis Karampelas, Hellenic American University, Greece Mehmet Kaya, Firat University, Turkey Yiping Ke, The Chinese University of Hong Kong, China Larry Kerschberg, George Mason University, USA Taghi Khoshgoftaar, Florida Atlantic University, USA Keivan Kianmehr, University of Calgary, Canada Chris Kimble, Euromed Management, France Peer Krger, Universitt Mnchen, Germany Adam Krzyzak, Concordia University, Canada Rui Kuang, University of Minnesota, USA Yau-Hwang Kuo, National Cheng-Kung University, Taiwan Christine Largeron, University Jean Monnet, France Kim S. Larsen, University of Southern Denmark, Denmark Hady W. Lauw, Microsoft Research, USA Chung-Hong Lee, National Kaohsiung University of Applied Sciences, Taiwan Hahn-Ming Lee, National Taiwan University of Science and Technology, Taiwan Kwan Hong Lee, MIT, USA Juergen Lerner, University of Konstanz, Germany Gang Li, Deakin University, Australia Jun Li, Nanyang Technological University, Singapore Ming Li, Nanjing University, China Hwee Ling Lim, The Petroleum Institute, United Arab Emirates Wen-Yang Lin, National University of Kaohsiung, Taiwan Xumin Liu, Rochester Institute of Technology, USA Zongmin Ma, Northeastern University, China Massimo Marchiori, UNIPD and UTILABS, Italy Byron Marshall, Oregon State University, USA Yutaka Matsuo, University of Tokyo, Japan Haris Memic, University of Essex, UK Peter Mutschke, GESIS-IZ, Germany Shinsuke Nakajima, Kyoto Sangyo University, Japan Federico Neri, Synthema S.r.l., Italy Darko Obradovic, German Research Center for Artificial Intelligence, Germany Kok-Leong Ong, Deakin University, Australia Tansel zyer, TOBB, Turkey Marcin Paprzycki, IBS PAN and WSM, Poland
Gregory Piatetsky-Shapiro, KDnuggets Marc Plantevit, LIRIS-CNRS, France Laura Pullum, Oak Ridge National Laboratory, USA Huzefa Rangwala, George Mason University, USA Christopher Rhodes, Imperial College, United Kingdom Christopher Rouff, Lockheed Martin Advanced Technology Laboratories, USA Alessandra Sala, University of California Santa Barbara, USA Antonio Sanfilippo, Pacific Northwest National Laboratory, USA Christoph Schmitz, Universitt Kassel, Germany Mohamed Shehab, University of North Carolina at Charlotte, USA Jun Shen, University of Wollongong, Australia Wanita Sherchan, CSIRO, Australia Mohammed Yakoob Siyal, Nanyang Technological University, Singapore Andy Song, RMIT University, Australia Von-Wun Soo, National TsingHua University, Taiwan Jerzy Surma, Warsaw School of Economics, Poland Andrea Tagarelli, University of Calabria, Italy Lei Tang, Yahoo! Lab, USA Jie Tang, Tsinghua University, China Alex Thomo, University of Victoria, Canada Hannu Toivonen, University of Helsinki, Finland Frank S.C. Tseng, National Kaohsiung First University of Science and Technology, Taiwan Lorna Uden, University of Staffordshire, UK Julien Velcin, University Lyon, France Chris Volinsky, AT&T, USA Dorothea Wagner, Karlsruhe Institute of Technology, Germany Christian Waldstrom, Aarhus School of Business, Denmark Jianyong Wang, Tsinghua University, China Kai-Yu Wang, Brock University, Canada Tien-Chin Wang, National Kaohsiung University of Applied Sciences, Taiwan Raymond Chi-Wing Wong, Hong Kong University of Science and Technology, HK Chih-Hung Wu, National University of Kaohsiung, Taiwan Hui-Ju Wu, National Changhua University of Education, Taiwan S. Felix Wu, University of California, Davis, USA Jennifer Xu, Bentley College, USA Pingkun Yan, Philips Research, USA Hsieh-Hua Yang, Oriental Institute of Technology, Taiwan Daniel Zeng, University of Arizona, USA Min-Ling Zhang, Hohai University, China Zhongfei Mark Zhang , SUNY Binghamton, USA Kaidi Zhao, Amazon.com Inc, USA Qiangfu Zhao, University of Aizu, Japan Lina Zhou, University of Maryland Baltimore County, USA Xiangmin Zhou, CSIRO, Australia Haibin Zhu, Nipissing University, Canada Peidong Zhu, National University of Defense Technology, China Xingquan Zhu, CSIRO, Australia
10
External Reviewers
ASONAM 2011
Hijbul Alam Sam Blasiak Shumo Chu Pasquale De Meo Huiji Gao Robert Grke Xia Hu Andrey Kan Shamanth Kumar Ofrit Lesser Yingming Li Lin Liu Pierre-Nicolas Mougel Yu Peng Harald Psaier Kun Qian Zeehasham Rasheed Rouff Tanwistha Saha Anna Stavrianou Jiliang Tang Ze Tian Shiro Uesugi Chao-Lin Wu Zhiqiang Xu Liangliang Ye Yang Yu
Sofia Angeletou Haiquan Chen Kamalika Das Bolin Ding Toader David Gherasim Zhouzhou He Ioana Hulpus Daisuke Kitayama Yi-Horng Lai Alex Leung Shoude Lin Claudia Marinica Kenta Oku Giovanni Ponti Rami Puzis Pir Abdul Rasool Queshi Jia Rong Ning Ruan Marian Scuturici Xiaoyuan Su Mohammad A. Tayebi Martin Treiber Jinlong Wang Yang Xiang Ming Yang Xiao Yu Jianwei Zhang
11
A Message from the General Chairs

ASONAM 2011
Welcome to ASONAM 2011 the 2011 International Conference on Advances in Social Network Analysis and Mining. ASONAM 2011 builds on the great success of ASONAM 2009, which was held in Athens, Greece, in July 2009, and ASONAM 2010, which was held in Odense, Denmark, in August 2010. The conference provides an excellent opportunity to meet fellow researchers and practitioners from a variety of social network analysis and mining fields to form new collaborations and to exchange research ideas and practices. It is our great pleasure to report that there are six keynote speakers, from four continents, invited to the conference. Professor Jiawei Han from University of Illinois at Urbana-Champaign, USA, is well-known for his work on data mining and information network analysis and for his book, "Data Mining: Concepts and Techniques". Two distinguished speakers, Johnny Engell-Hansen (Head of Operations Unit Council of the European Union) and Arno H. P. Reuser (Chief of Open Source Intelligence of Defense Intelligence and Security Service) are invited from Europe. Professor Philippa Pattison from University of Melbourne, Australia, is a Fellow of the Academy of the Social Sciences in Australia in 1994. In addition, two professors, Professor Yutaka Matsuo of University of Tokyo and Professor Ming-Syan Chen from National Taiwan University are invited from Asia. We also wish to thank them for accepting our invitation. We are very happy that we can present such a strong group of keynote speakers at ASONAM 2011. This year we will also present awards for the best papers at the conference based on the reviews and the presentations. We wish to thank Springer for sponsoring this award. The success of ASONAM 2011 depends on the people and organizations that support it. We must thank all the volunteers who helped organize this conference. In particular, we thank Program Chairs I-Hsien Ting, Nasrullah Memon and Reda Alhajj, who together with the Program Committee, created a great technical program. In addition, we would like to thank Publicity Chairs Malek Haroud, Tsau-Young Lin, Tansel zyer, Jon Rokne, Ying-Feng Kuo, and Chien-Hsing Wu; Publications Chairs Panagiotis Karampelas and Yu-Hui Tao; Web Chair Hsin-Chang Yang; Workshop Chairs Yingzi Jin, Kai Wang, and Shu-Chen Yang; and last but not least Local Arrangements Chairs Chian-Hsueng Chao, Han-Wei Hsiao, Hsing-Tzu Lin, Shing-Tai Pan and Chin-Fu Kuo. The conference would not be possible without sponsors. The academic sponsors include National University of Kaohsiung, National Science Council of ROC, Ministry of Education of ROC, State University of New York at Stony Brook, USA, University of Southern Denmark, Denmark, University of Calgary, Canada, Hellenic American University of Greece, Global University of Lebanon, and Taiwan Association for Web Intelligence Consortium. The conference is organized in collaboration with IEEE Computer Society, IEEE technical committees on awareness computing, data engineering, granular computing (technical co-sponsorship), and ACM SIGCHI, SIGKDD, SIGSPATIAL, and SIGWEB. We would also like to thank the industrial sponsors, Kaohsiung city government, MEET Taiwan, Bureau of Foreign Trade, Web Genie, Springer, and SolventoSOFT. The ASONAM conference series will continue next year with ASONAM 2012 to be held in Turkey. We hope to meet you all again!
Tzung-Pei Hong, Leon Shyue-Liang Wang, and Uffe K. Wiil General Chairs
12
A Message from the Program Chairs

ASONAM 2011
Welcome to ASONAM 2011! This year, we move the venue of ASONAM from Europe to Asia in order to provide an opportunity for the participants from different continents to share their research about social network analysis and mining. After the great success events of ASONAM 2009 in Athens, Greece and ASONAM 2010 in Odense, Denmark, Kaohsiung, Taiwan is the place where to continue the journey of this event. We deeply appreciate the local team from National University of Kaohsiung to make ASONAM 2011 success. ASONAM is intended to address important aspects of interest to practitioners and researchers with a specific focus on the emerging trends and industry needs associated with social network analysis and mining. The conference solicits experimental and theoretical work on social network analysis and mining, including: (1) using graph theory and machine learning approaches or multi-agent based simulation for social network modeling, constructing scalable, customizable social network infrastructure, as well as the identification and discovery of dynamic growth and evolution patterns; (2) data mining advances on the discovery and analysis of communities, on personalization for solitary activities (like search) and social activities (like discovery of potential friends), on the analysis of user behavior in open fora (like conventional sites, blogs and fora) and in commercial platforms (like e-auctions) and on the associated security and privacy-preservation challenges. ASONAM provides an interdisciplinary venue that sets the stage for sociologists, behavioral scientists, computer scientists, psychologists, anthropologists, and information systems scientists to exchange ideas, learn new concepts, and develop new methodologies. Activities included speeches from keynote speakers, oral and poster presentations. The main goal of ASONAM is to study and elaborate synergies between interdisciplinary venues as discussed above, and to provide a glimpse at the state of the art in the area. This year, we continue to keep the tradition of high quality conference and to maintain the acceptance rate of 25%. The success would have not been possible without the full support of a strong international program committee that was expanded this year to include more research leaders who all worked extremely hard to evaluate the submitted papers. More than 120 papers will be presented and discussed in Kaohsiung, Taiwan during 25-27 July 2011. The manuscripts reflect the evolving state of social network analysis and mining; they report the original discoveries of researchers from more than 24 countries. Each contributor to this conference does indeed add fresh views and thoughts, challenges our beliefs, and encourages further exploration and innovation on our part. We are grateful to each participant for providing the opportunity to share the invaluable ideas. With the hope that this conference will open even wider awareness of knowledge, we welcome you to the National University of Kaohsiung campus to enjoy the wonderful program of ASONAM 2011 and encourage you to start working on your submission to ASONAM 2012; we look forward to meeting you again in July 2012, Turkey.
Reda Alhajj, Nasrullah Memon, and I-Hsien Ting Program Chairs
13
Conference Program At a Glance

ASONAM 2011 Featured Events Meals and Social Events
Day 1: July 25 (Monday)

08:00-09:00 09:00-09:30 09:30-10:30 Registration Opening Session (Room B101) Keynote Speech 1 (Room B101) Chair: Prof. Reda Alhajj Prof. Philippa Pattison, The University of Melbourne, Australia Title: Statistical Models for the Analysis of Social Networks 10:30-10:50 10:50-12:30 Coffee Break (Room 102, 103, 104) Parallel Sessions A Session A1: Contextual Social Network Analysis (I) Chair: Prof. Georgios Lappas (Room 418) Session A2: Scalability in Social Network Analysis Chair: Prof. Nitesh Chawla (Room 419) Session A3: (Workshop) The First International Workshop on Mobile Social Network Chair: Dr. Kun-Lung Wu (Room 420) Session A4: Information Acquisition and Establishment of Social Networks Chair: Prof. Chien-Hsing Wu (Room 422) 12:30-14:00 14:00-15:00 Lunch (Room 102, 103, 104) Keynote Speech 2 (Room B101) Chair: Prof. Tansel zyer Prof. Yutaka Matsuo, The University of Tokyo, Japan Title: Social Network Mining for People Search 15:00-15:20 15:20-17:20 Coffee Break (Room 102, 103, 104) Parallel Sessions B Session B1: Recommendation (I) Chair: Dr. Johann Stan (Room 418) Session B2: Privacy and Security Chair: Prof. Guido Barbian (Room 419) Session B3: Dynamic Social Networks (I) Chair: Prof. Yu-Hui Tao (Room 420) Session B4: (Workshop) Cyberpsychological Analysis of Social Network Analysis in Applications Chair: Prof. Shiro Uesugi (Room 422) 18:30-21:00 Conference Reception (Garden Villa Hotel)
14
Day 2: July 26 (Tuesday)

08:00-09:00 09:00-10:00 Registration Keynote Speech 3 (Room B101) Security Service Title: A Changing Nature of Warfare Requires a Change of Mindset of Defense Intelligence and the Role of OSINT and Social Networks therein 10:00-10:20 10:20-12:00 Poster Session (Room 101) Coffee Break (Room 102, 103, 104) Parallel Sessions C Session C1: Contextual Social Network Analysis (II) Chair: Prof. Chung-Hong Lee (Room 418) Session C2: Recommendation (II) Chair: Prof. Angelos Stavrou (Room 419) Session C3: Dynamic Social Networks (II) Chair: Dr. Mi-Yen Yeh (Room 420) Session C4: Community Discovery and Analysis (I) Chair: Prof. Hsin-Chang Yang (Room 422) 12:00-13:30 13:30-14:30 Poster Session (Room 101) Lunch (Room 102, 103, 104) Keynote Speech 4 (Room B101) Chair: Prof. Vincent S. Tseng Prof. Jiawei Han, University of Illinois at Urbana-Champaign, USA Title: Towards Integrated Mining of Multiple Social and Information Networks 14:30-18:30 19:00-21:30 Kaohsiung City Tour Conference Banquet and Best Paper Award (The Splendor Hotel) Chair: Prof. Nasrullah Memon Arno H. P. Reuser, Chief, Open Source Intelligence, Defense Intelligence and
15
Day 3: July 27 (Wednesday)

08:00-09:00 09:00-10:00 Registration Keynote Speech 5 (Room B101) Union Title: Can Early Warning be Improved by Enhancing Open Source Intelligence through Better Exploitation of Societal Data and Information ? 10:00-10:20 10:20-12:00 Coffee Break (Room 102, 103, 104) Parallel Sessions D Session D1: (Workshop) The 1st International Workshop on Cloud Computing in Social Networks Chair: Dr. Wen-Chih Tsai (Room 418) Session D2: (Workshop) The First Workshop on Social Network Analysis in Applications (I) Chair: Prof. Jason Jung (Room 419) Session D3: Community Discovery and Analysis (II) Chair: Prof. Nasrullah Memon (Room 420) Session D4: Temporal Analysis on Social Network Topologies Chair: Prof. Edgar Fuller (Room 422) 12:00-13:30 13:30-14:30 Lunch (Room 102, 103, 104) Keynote Speech 6 (Room B101) Chair: Prof. Ambuj K. Singh Prof. Ming-Syan Chen, Director, Research Center for Information Technology Innovation, Academia Sinica, Taiwan Title: Information Processing in Social Networks 14:30-14:50 14:50-16:50 Coffee Break (Room 102, 103, 104) Parallel Sessions E Session E1: Application of SNA Chair: Prof. Tansel zyer (Room 418) Session E2: Misbehavior and Crime Detection Chair: Dr. M. Saravanan (Room 419) Session E3: (Workshop) The 3rd International Workshop on Mining Social Networks for Decision Support Chair: Prof. Yuan-Chu Hwang (Room 420) Session E4: (Workshop) The First Workshop on Social Network Analysis in Applications (II) Chair: Prof. Przemyslaw Kazienko (Room 422) 16:50-17:10 17:10-17:40 Coffee Break (Room 102, 103, 104) Closing Session (Room B101) Chair: Prof. Von-Wun Soo Johnny Engell-Hansen, Head of Operation Unit, Council of the European
16
Keynote Speakers
ASONAM 2011
Keynote
Statistical Models for the Analysis of Social Networks

Philippa Pattison The University of Melbourne, Australia
09:30-10:30 Chair:
Monday, July 25, 2011 Prof. Reda Alhajj
Room: B101
Abstract
The paper will review a flexible framework for the analysis of social network data based on exponential random graph models and will present several recent developments that enhance the capacity of the framework to yield theoretically principled and empirically plausible models for social networks and network-based social processes. In particular, a hierarchy of potential models for social networks is developed and it shown how this hierarchy can be used (a) to estimate models from empirical social network data and evaluate model fit, and (b) extend this capacity to the case of certain types of sampled data.
Short Bio
Professor Philippa (Pip) Pattison is a quantitative psychologist recognised for her work in the development of mathematical models for social and behavioural phenomena, particularly for social networks and network-based social processes. Pip completed both a Bachelor of Science (Hons) and a PhD at the University of Melbourne. Pip served as Head of the School of Behavioural Sciences at the University of Melbourne from 2002-2003, and from 2007-2008 was the President of the Universitys Academic Board. In 2009 she was appointed as the Pro Vice-Chancellor (Learning & Teaching) at the University of Melbourne. In May 2011, Professor Pattison was appointed as Deputy Vice-Chancellor (Academic). As Deputy Vice Chancellor (Academic), Pip is responsible for leading the University's learning and teaching strategy and consolidating the implementation of Melbourne Model programs. She works in collaboration with colleagues across the University to ensure that its academic programs meet the high standards in teaching and learning that have been set for them and, in particular, achieve their distinctive learning outcomes. Pip was elected a Fellow of the Academy of the Social Sciences in Australia in 1995.
17
Keynote
Social Network Mining for People Search

Yutaka Matsuo The University of Tokyo, Japan
14:00-15:00 Chair:
Monday, July 25, 2011 Prof. Tansel zyer
Room: B101
Abstract
In this talk, I shall introduce several techniques used to mine social networks from Web information. The objective of the research is the mining of large-scale entity-relation networks from the Web to support advanced knowledge integration, structuring, and retrieval. The key feature of the algorithm is its utilization of a search engine public interface with machine-learning and text-processing techniques. This talk presents a summary of our studies reported at several past conferences including WWW, IJCAI, and AAAI. It will cover the technologies underlying the most popular people search application in Japan, called SPYSEE, which has 20 million page-views per month.
Short Bio
Yutaka Matsuo is an Associate Professor at the Institute of Engineering Innovation, The University of Tokyo. He received his BS, MS, and PhD degrees from The University of Tokyo in 1997, 1999, and 2002 (supervised by Prof. Ishizuka). He worked at the National Institute of Advanced Industrial Science and Technology (AIST) during 20022007. His emphases of study are web mining (specifically social network mining), text processing, and semantic web in the context of artificial intelligence research. Prof. Matsuo is a prominent young researcher in the information technology field in Japan. He received the Japanese Society for Artificial Intelligence (JSAI) Best Paper Award in 2002, the JSAI Anniversary Project Award in 2006, and Information Processing Society of Japan (IPSJ) Nagao Special Researcher Award in 2008. He joined the editorial committee of JSAI in 2004, and currently serves as Associate Editor-in-Chief. He received a Japan Society for the Promotion of Science (JSPS) Postdoctoral Fellowship for Research Abroad in 2005 and remained for two years at the Center for the Study of Language and Information (CSLI) at Stanford University. He is a PC member of several conferences and is an editor of journals including the International World Wide Web Conference (WWW), International Conference on Artificial Intelligence (IJCAI), and IEEE Transactions on Knowledge Engineering and Data Mining (TKDE).
18
Keynote
A Changing Nature of Warfare Requires a Change of Mindset of Defense Intelligence and the Role of OSINT and Social Networks therein
Arno H. P. Reuser Chief, Open Source Intelligence, Defence Intelligence and Security Service
09:00-10:00 Chair:
Tuesday, July 26, 2011 Prof. Nasrullah Memon
Room: B101
Abstract
There is a radical change underway in which warfare is being conducted. That change is there, it has been there for quit some time and it will most probably continue to grow in importance and significance. It is called Computer Network Operations (CNO), or, information warfare or cyber warfare. Two forms are of particular interest: computer network attack (CNA: attacking, changing and possibly destroying systems of the opposing forces) and computer network exploitation (CNE: cyber espionage, or finding and taking sensitive information from computer networks). For every threat there are in reality two threats, the second one being the vulnerability to attack by its victims, due to lack of awareness, training and education. Social networks play a crucial role in CNO especially for the deployment of cyber weapons such as identity theft and the dissemination of malware to create computer zombie networks. Two traditional intelligence collection disciplines need to change their mindset: SIGINT and OSINT as the logical foundation of CNO. The keynote speech will address these issues and explain the important relationship between social networks
Short Bio
Arno Reuser is a professional librarian / information professional with more than 30 years experience in information handling and processing. He founded the Open Source Intelligence Unit of the Dutch Defence Intelligence & Security Service about 15 years ago and still heads it today. Mr. Reuser holds a bachelor degree in librarianship and has completed many courses in digital information management, Internet search strategies, update workshops etc. He learned the technical requirements of today's digital world by learning how to write software, program scripts to automate tasks, building websites, getting the most out of the Internet by studying network theory, all in support of OSINT information management. In addition to his work with the Dutch Defence and Intelligence Service, Arno established his own company "Reusers Information Services" in conjunction with his current position as head of OSINT. RIS primary goal is to teach Open Source Intelligence (systematic searching, finding and reporting with security in mind) and provide consultancy for government and private sector institutions worldwide. Arno has an extensive history of teaching OSINT, and OSINT training has been a core focus of his professional activities for decades. Today, he teaches OSINT, search strategies, information handling and security to a wide range of audiences. He travels
19
regularly to the United States, Switzerland, Austria, and United Kingdom to teach to a wide range of multilingual, multicultural audiences and is thus used to communicating with people from different backgrounds and possessing different language skills. Arno is a recognized expert on OSINT and speaks regularly at international conferences and workshops on the organization and maintenance of Open Source Intelligence Services, at home and abroad, for a diverse audience such as international organizations, government institutes, intelligence, military, and information professionals. Arno is the owner and maintainer of Reuser's New Repertorium, an online categorised annotated listing of intel sources and search engines. He also wrote his own multisearch search engine Isolde to enable building block search strategies, and is the owner and moderator of NEDBIB-L listserv discussion list with 2000 participants. Arno writes a regular column and has written journal articles and book chapters on OSINT.
20
Keynote
Towards Integrated Mining of Multiple Social and Information Networks

Jiawei Han University of Illinois at Urbana-Champaign, USA
13:30-14:30 Chair:
Tuesday, July 26, 2011 Prof. Vincent S. Tseng
Room: B101
Abstract
People and information entities in the real world are interconnected, forming complex, multiple social and information networks. There have been a lot of studies on mining single, independent, homogeneous social and information networks where objects and links are either treated as of the same type, such as friends linking with friends, or treated indiscriminatively, without structural or type distinction. However, real-world objects and links often belong to distinct types, such as students, professors, courses, departments, teach and advise in a university network, and such typed networks form multiple, structured, heterogeneous social and information networks. We explore methodologies on mining such structured multiple social and information networks and introduce several interesting new mining methodologies, including integrated ranking and clustering, classification, role discovery, data integration, data validation, and similarity search. We show that integrated mining of multiple interconnected social and information networks are powerful at uncovering critical knowledge hidden in large and multiple, interconnected networks.
Short Bio
Jiawei Han, Professor of Computer Science, University of Illinois at Urbana-Champaign. He has been researching into data mining, information network analysis, database systems, and data warehousing, with over 500 journal and conference publications. He has chaired or served on many program committees of international conferences, including PC co-chair for KDD, SDM, and ICDM conferences, and Americas Coordinator for VLDB conferences. He is currently the founding Editor-In-Chief of ACM Transactions on Knowledge Discovery from Data and as the Director of Information Network Academic Research Center supported by U.S. Army Research Lab. He is a Fellow of ACM and IEEE, and received 2004 ACM SIGKDD Innovations Award, 2005 IEEE Computer Society Technical Achievement Award, and 2009 IEEE Computer Society Wallace McDowell Award. His book "Data Mining: Concepts and Techniques" (2nd ed., Morgan Kaufmann, 2006) has been adopted as a textbook worldwide.
21
Keynote
Can Early Warning be Improved by Enhancing Open Source Intelligence through Better Exploitation of Societal Data and Information ?
Johnny Engell-Hansen Head of Operation Unit, Council of the European Union
09:00-10:00 Chair:
Wednesday, July 27, 2011 Prof. Von-Wun Soo
Room: B101
Abstract
Early warning as a concept can be applied to crises and crisis management in many different areas; political, economic, natural disasters, environmental, societal, health, etc. This presentation will focus on its application where the gradual destabilisation of a country or region has the potential to lead to societal unrest and/or violent conflict. The societal deterioration of a country or a region in principle goes through three phases: the stable phase, the fragile phase and the crisis phase. The methodology used to analyse and assess the evolution of societal status differs depending on the "phase". In the (relatively) stable phase the situation will typically be assessed by means of a number of pre-determined parameters - "indicators". The gradual deterioration of the building blocks, which under normal circumstances ensure a viable and cohesive society as well as good relations with neighbouring countries; e.g. political, ideological, cultural, religious, social, economic, etc. is tracked and compared. This model assumes that each parameter can fairly easily be monitored and scored. To a large extent the model can then be automated and almost mechanically applied. This way of situation monitoring can be described as the quantitative model. To determine the relative state-of-affairs in this phase each indicator is monitored and scored. The sum of scores will, in principle, tell us whether a crisis is approaching. And at least in theory - the extrapolation of deteriorating indicators enables the analyst to predict the breaking point, i.e. the point at which a crisis can be declared. If a sufficient number of parameters move from green to amber or red a crisis is per definition unfolding. The advantage of the quantitative model is that it can to a large degree be automated, enabling you to cover a large number of countries and situations with relatively modest resources. The disadvantage is that it is a fairly blunt instrument and experience has shown that the model will sometimes (often) fail to detect sudden, rapidly unfolding crises in a timely fashion. At the other end of the spectrum, the crisis phase, where the evolving crisis' breaking point is imminent, experience has shown that objective parameters - the indicators become more or less...
22
Short Bio
Within the EU External Action Service, Johnny Engell-Hansen is currently Head of Duty and Awareness Division in the EU Situation Centre and also Head of the EU Situation Room. Responsibilities include; monitoring and assessing world-wide events on a 24/7 basis; Early Warning and Crisis Response; alerting the EU High Representative, senior EU officials and EU Member States to politically significant events; Open Sources analyses; Deployable teams to ensure enhanced crisis information flow from theatre in a crisis situation; Provision of core infrastructures (human and material) to support EU policy level consultations and coordination in case the EU Emergency and Crisis Coordination Arrangements are triggered; and cooperation and information exchange with partners in EU institutions, EU Member States and other International Organisations. Johnny Engell-Hansen has participated in work to support the development of African Union "Continental Early Warning System". He has served as an adviser to the EU border management agency FRONTEX on the setting up of its own Situation Centre. Johnny Engell-Hansen has been a co-initiator in the creation of a platform for cooperation and information exchange between bodies within International Organisations responsible for "early warning" and "crisis response". He has played a leading role in the "Budapest Club"- a forum created to enhance the exploitation of Open Sources information among EU government institutions and has been a frequent speaker / participant in various conferences and workshops dealing with "Open Source Intelligence", "Early Warning" and "Crisis Response". Within the EU General Secretariat of the Council Johnny Engell-Hansen has previously held positions in departments dealing with Energy Policy and Organisational Development. In the framework of an exchange programme he was seconded to the German Federal Ministry of Foreign Affairs and the German Federal Ministry of Defence in 2002. Prior to joining the EU General Secretariat of the Council Johnny Engell-Hansen was a career officer in the Danish Armed Forces. He was, among other things, seconded to the EU Monitoring Mission in ex-Yugoslavia in 1993 where he served in Croatia, Bosnia-Herzegovina and Albania.
23
Keynote
Information Processing in Social Networks

Ming-Syan Chen Director, Research Center for Information Technology Innovation, Academia Sinica, Taiwan
13:30-14:30 Chair:
Wednesday, July 27, 2011 Prof. Ambuj K. Singh
Room: B101
Abstract
In the current social network, a user may have hundreds of friends and find it very time consuming to categorize and tag every friend manually. When a user is going to initiate an activity by issuing a corresponding query, he/she needs to consider the relationship among candidate attendees to find a group of mutually close friends. Meanwhile, he/she also needs to consider the schedule of candidate attendees to find an activity period available for all attendees. It would certainly be desirable if the efficiency of such process is improved. In this talk, information query in social networks will be reviewed. We shall also introduce a novel social visualization system, SocFeedViewer, which is able to automatically cluster friends based on the number of mutual acquaintances and then systematically shows the social information, thus allowing users of having a whole picture quickly. When a user decides to initiate an activity among a cluster of friends, the user can further issue a Social-Temporal Group Query (STGQ), and the proposed algorithm STGSelect will return a group of attendees with minimum total social distance, together with a suitable time period which is available for all attendees. The STGQ is known to be an NP-hard problem; however, STGSelect is still able to find the optimal answer efficiently and reduce considerable processing time with proposed strategies.
Short Bio
Ming-Syan Chen received the B.S. degree in electrical engineering from National Taiwan University, Taipei, Taiwan, and the M.S. and Ph.D. degrees in Computer, Information and Control Engineering from The University of Michigan, Ann Arbor, MI, USA, in 1985 and 1988, respectively. He is now a Distinguished Research Fellow and the Director of Research Center of Information Technology Innovation (CITI) in the Academia Sinica, Taiwan, and is also a Distinguished Professor jointly appointed by EE Department, CSIE Department, and Graduate Institute of Communication Eng. (GICE) at National Taiwan University. He was a research staff member at IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA from 1988 to 1996, the Director of GICE from 2003 to 2006, and also the President/CEO of Institute for Information Industry (III), which is one of the largest organizations for information technology in Taiwan, from 2007 to 2008. His research interests include databases, data mining, cloud computing, and multimedia networking, and he has published more than 300 papers in his research areas. In addition to serving as program chairs/vice-chairs and keynote/tutorial speakers in many international conferences, Dr. Chen was an associate editor of IEEE TKDE, VLDB Journal, KAIS, and also JISE, is currently the Editor-in-Chief of the International Journal
24
of Electrical Engineering (IJEE), and is a Distinguished Visitor of IEEE Computer Society for Asia-Pacific from 1998 to 2000, and also from 2005 to 2007. Dr. Chen is now also serving as the Chief Executive Officer of Networked Communication Program, which is a national program coordinating several primary activities in information and communication technologies in Taiwan. He holds, or has applied for, eighteen U.S. patents and seven ROC patents in his research areas. He is a recipient of the Academic Award of the Ministry of Eduation, the NSC (National Science Council) Distinguished Research Award, Pan Wen Yuan Distinguished Research Award, Teco Award, Honorary Medal of Information, and K.-T. Li Research Breakthrough Award for his research work, and also the Outstanding Innovation Award from IBM Corporate for his contribution to a major database product. He was also elected as a Chair Professor by National Chung Hsing University. He received numerous awards for his research, teaching, inventions and patent applications. Dr. Chen is a Fellow of ACM and a Fellow of IEEE.
25
Conference Program
ASONAM 2011
Featured Events Meals and Social Events Day 1: July 25 (Monday)

08:00-09:00 Registration 09:00-09:30 Opening Session (Room B101) 09:30-10:30 Keynote Speech 1 (Room B101) Chair: Prof. Reda Alhajj Prof. Philippa Pattison, The University of Melbourne, Australia Title: Statistical Models for the Analysis of Social Networks 10:30-10:50 Coffee Break (Room 102, 103, 104) 10:50-12:30 Parallel Sessions A Session A1: Contextual Social Network Analysis (I) Room 418 Session Chair: Prof. Georgios Lappas 1. Matteo Magnani and Luca Rossi The ML-model for Multi-Layer Social Networks 2. Yuto Yamaguchi, Toshiyuki Amagasa and Hiroyuki Kitagawa Tag-based User Topic Discovery using Twitter Lists 3. Kathy Macropol and Ambuj Singh Content-based Modeling and Prediction of Information Dissemination 4. Marina Danilevsky, Joshua Hailpern and Jiawei Han SCENE: Structural Conversation Evolution NEtwork 5. Yu-Chin Liu, Ti-Lin Chueh and Yun-Shan Cheng A Hybrid Approach to Discover MEC Interview Data - With the Hierarchical Value Map of Social Networking Sites as an Example Session A2: Scalability in Social Network Analysis Room 419 Session Chair: Prof. Nitesh Chawla 1. Ryan N. Lichtenwalter and Nitesh V. Chawla DisNet: A Framework for Distributed Graph Computation 2. Ting Ting Qin and Satoshi Fujita Automatic Tag Attachment Scheme for Efficient File Search in Peer-to-Peer File Sharing Systems 3. Matthias Broecheler, Andrea Pugliese and V.S. Subrahmanian Probabilistic Subgraph Matching on Huge Social Networks 4. Piotr Brdka, Pawe Stawiak and Przemyslaw Kazienko Shortest Path Discovery in the Multi-layered Social Network 5. Bo Yang and Jiming Liu Discovering Explorative Patterns from Real World Complex Networks Session A3: (Workshop) The First International Workshop on Mobile Social Network Room 420 Session Chair: Dr. Kun-Lung Wu
26
1.
12:30-14:00 14:00-15:00
15:00-15:20 15:20-17:20
Yao-Hua Ho, Yao-Chuan Wu, Meng Chang Chen, Tsun-Jui Wen and Yeali S. Sun GPS Data Based Urban Guidance 2. Bi-Ru Dai, Chang-Yi Lee and Chih-Heng Chung A Framework of Recommendation System Based on both Network Structure and Messages 3. M. Saravanan, S. Buveneswari, S. Divya, and V. Ramya Bayesian Filters for Mobile Recommender Systems 4. Cheng-Ta Yang, Wen-Sheng Chang, Fan-Ning Cheng and Wei-Guang Teng Assessing Media Relevance via Eye Tracking 5. Jianhua Shao Mobile Engagement Session A4: Information Acquisition and Establishment of Social Networks Room 422 Session Chair: Prof. Chien-Hsing Wu 1. Mathilde Forestier, Julien Velcin and Djamel A. Zighed Extracting Social Networks to Understand Interaction 2. Baoshi Yan, Lokesh Bajaj and Anmol Bhasin Entity Resolution Using Social Graphs for Business Applications 3. Michael Farrugia, Neil Hurely and Aaron Quigley SNAP: Towards a Validation of the Social Network Assembly Pipeline 4. Antonio Rivero Ostoic Dyadic Patterns in Multiple Networks Lunch (Room 102, 103, 104) Keynote Speech 2 (Room B101) Chair: Prof. Tansel zyer Prof. Yutaka Matsuo, The University of Tokyo, Japan Title: Social Network Mining for People Search Coffee Break (Room 102, 103, 104) Parallel Sessions B Session B1: Recommendation (I) Room 418 Session Chair: Dr. Johann Stan 1. Yizhou Sun, Rick Barber, Manish Gupta, Charu Aggarwal and Jiawei Han Co-Author Relationship Prediction in Heterogeneous Bibliographic Networks 2. Nicola Barbieri Regularized Gibbs Sampling for User Profiling with Soft Constraints 3. Lin Chen, Richi Nayak and Yue Xu A Recommendation Method for Online Dating Networks Based on Social Relations and Demographic Information 4. Yin-Fu Huang and San-Des Lin Applying Multidimensional Association Rule Mining to Feedback-based Recommendation Systems 5. Kai-Yu Wang, Narongsak Thongpapanl, Hui-Ju Wu and I-Hsien Ting Identifying Structural Heterogeneities Between Online Social
27
Networks For Effective Word-of-Mouth Marketing 6. Stamatina Thomaidou and Michalis Vazirgiannis Multiword Keyword Recommendation System for Online Advertising Session B2: Privacy and Security Room 419 Session Chair: Prof. Guido Barbian 1. Bruce Kapron, Gautam Srivastava, and S. Venkatesh Social Network Anonymization via Edge Addition 2. Guido Barbian Assessing Trust by Disclosure in Online Social Networks 3. Mohammad A. Tayebi, Laurens Bakker, Uwe Glsser, and Vahid Dabbaghian Locating Central Actors in Co-offending Networks 4. Sean Chester and Gautam Srivastava Social Network Privacy for Attribute Disclosure Attacks 5. Hsin-Chang Yang and Chung-Hong Lee Post-Level Spam Detection for Social Bookmarking Web Sites 6. Kyung Soo Cho, Jae Yeol Yoon, Iee Joon Kim, Ji Yeon Lim and Ung-Mo Kim Mining Information of Anonymous User on a Social Network Service Session B3: Dynamic Social Networks (I) Room 420 Session Chair: Prof. Yu-Hui Tao 1. Darcy Davis, Ryan Lichtenwalter and Nitesh V. Chawla Multi-Relational Link Prediction in Heterogeneous Information Networks 2. Juan Lang and S. Felix Wu Social Network User Lifetime 3. Elsa Negre, Rokia Missaoui and Jean Vaillancourt Predicting Social Network Structure once a Node is Deleted 4. Tomoyuki Yuasa and Susumu Shirayama A New Analysis Method for Simulations Using Node Categorizations 5. Pei-Chun Ko and Vincent Buskens Dynamics of Adolescent Friendships: The Interplay between Structure and Gender 6. Usha Sridhar and Sridhar Mandyam Information Sources Driving Social Influence: A New Model for Belief Learning in Social Networks Session B4: (Workshop) Cyberpsychological Analysis of Social Network Analysis in Applications Room 422 Session Chair: Prof. Shiro Uesugi 1. Shiro Uesugi Effect of Personal Traits in the Usages of SNS 2. Yu-Lung Wu, Yu-Hui Tao, Ching-Pu Lee, Pei-Chi Yang and Guo-Shin Huang The Moderating Role of Virtual Community Cohesion and Critical Mass on the Link between Online-game Website Service Quality
28
18:30-21:00
and Play Satisfaction 3. M.C. Chang and S.D. Gregor Encouraging Participation in Virtual Community via Classified Facilitation Mechanisms 4. Chian-Hsueng Chao Reconceptualizing the Internet Human Flesh Search Mechanism: Review of the Literature 5. Chia Sung Yen, Shih Chun Yang, Tien Hui Yeh and Yi Inn Sun The Organizational Justice Strategies to Affect Learning Performance and Self-efficacy 6. Chienhsing Wu, Shuchen Kao, Jiwe Chang and Kaeying Chen A Comparison of Cognitive Styles on the Behavior of Obtaining Knowledge: Field Independence Vs. Field Dependence Conference Reception (Garden Villa Hotel)
Day 2: July 26 (Tuesday)

08:00-09:00 Registration 09:00-10:00 Keynote Speech 3 (Room B101) Chair: Prof. Nasrullah Memon Arno H. P. Reuser, Chief, Open Source Intelligence, Defense Intelligence and Security Service Title: A Changing Nature of Warfare Requires a Change of Mindset of Defense Intelligence and the Role of OSINT and Social Networks therein 10:00-10:20 Poster Session (Room 101) Coffee Break (Room 102, 103, 104) 10:20-12:00 Parallel Sessions C Session C1: Contextual Social Network Analysis (II) Room 418 Session Chair: Prof. Chung-Hong Lee 1. Qing Ke, Yuxiao Dong and Bin Wu Efficient Search in Networks using Conductance 2. Christophe Thovex and Francky Trichet A Semantic and Multidisciplinary Model for Professional and Social Networks Analysis 3. Iraklis Varlamis and George Tsatsaronis Visualizing Bibliographic Databases as Graphs and Mining Potential Research Synergies 4. Charles Perez, Lemercier Marc, Babiga Birregah and Alain Corpel SPOT 1.0 : Scoring Suspicious Profiles On Twitter 5. Yuxiao Dong, Qing Ke, Bai Wang, and Bin Wu Link Prediction Based on Local Information Session C2: Recommendation (II) Room 419 Session Chair: Porf. Angelos Stavrou 1. Hendrik Wermser, Achim Rettinger and Volker Tresp Modeling and Learning Context-Aware Recommendation Scenarios using Tensor Decomposition 2. Jyi-Shane Liu and Ke-Chih Ning Applying Link Prediction to Ranking Candidates for High-Level Government Post 3. Daniel Chapsky
29
12:00-13:30 13:30-14:30
Leveraging Online Social Network Data and External Data Sources to Predict Personality 4. Johann Stan, Viet-Hung Do and Pierre Maret Semantic User Interaction Profiles for Better People Recommendation 5. Kyong Jin Shim, Kuo-Wei Hsu, and Jaideep Srivastava Modeling Player Performance in Massively Multiplayer Online Role-Playing Games: The Effects of Diversity in Mentoring Network Session C3: Dynamic Social Networks (II) Room 420 Session Chair: Dr. Mi-Yen Yeh 1. Chien-Tung Ho, Cheng-Te Li and Shou-De Lin Modeling and Visualizing Information Propagation in a Micro-blogging Platform 2. Georgios Lappas From Web Mining to Social Multimedia Mining 3. Tuan-Anh Hoang, Ee-Peng Lim, Palakorn Achananuparp, Jing Jiang, and Loo-Nin Teow Modeling Socialness in Dynamic Social Networks 4. Michalis Rallis and Michalis Vazirgiannis Rank Prediction in Graphs with Locally Weighted Polynomial Regression and EM of Polynomial Mixture Models 5. Shahadat Uddin and Liaquat Hossain Time Scale Degree Centrality: A Time-Variant Approach to Degree Centrality Measures Session C4: Community Discovery and Analysis (I) Room 422 Session Chair: Prof. Hsin-Chang Yang 1. Manish Gupta, Charu Aggarwal, Jiawei Han and Yizhou Sun Evolutionary Clustering and Analysis of Bibliographic Networks 2. Piotr Brdka, Stanisaw Saganowski and Przemyslaw Kazienko Group Evolution Discovery in Social Networks 3. Slah Alsaleh, Richi Nayak and Yue Xu Finding and Matching Communities in Social Networks Using Data Mining 4. Christos Giatsidis, Dimitrios Thilikos and Michalis Vazirgiannis Evaluating Cooperation in Communities with the k-core Structure 5. Yang Yang, Yizhou Sun, Saurav Pandit, Nitesh Chawla and Jiawei Han Is Objective Function the Silver Bullet? A Case Study of Community Detection Algorithms on Social Networks Poster Session (Room 101) Lunch (Room 102, 103, 104) Keynote Speech 4 (Room B101) Chair: Prof. Vincent S. Tseng Professor Jiawei Han, University of Illinois at Urbana-Champaign, USA Title: Towards Integrated Mining of Multiple Social and Information Networks
30
14:30-18:30 19:00-21:30
Kaohsiung City Tour Conference Banquet and Best Paper Award (The Splendor Hotel)
Day 3: July 27 (Wednesday)

08:00-09:00 Registration 09:00-10:00 Keynote Speech 5 (Room B101) Chair: Prof. Von-Wun Soo Johnny Engell-Hansen, Head of Operation Unit, Council of the European Union Title: Can Early Warning be Improved by Enhancing Open Source Intelligence through Better Exploitation of Societal Data and Information ? 10:00-10:20 Coffee Break (Room 102, 103, 104) 10:20-12:00 Parallel Sessions D Session D1: (Workshop) The 1st International Workshop on Cloud Computing in Social Networks Room 418 Session Chair: Dr. Wen-Chih Tsai 1. I-Hsien Ting, Chia-Hung Lin and Chen-Shu Wang Constructing A Cloud Computing Based Social Networks Data Warehousing and Analyzing System 2. Bo-Wen Yang, Wen-Chih Tsai, An-Pin Chen, and Singh Ramandeep Cloud Computing Architecture for Social Computing - a Comparison Study of Facebook and Google 3. Chien-Chih Tu and An-Pin Chen Building a Learning Games Network in Cloud Learning Platform based on Immigrant Education 4. Mao-Ping Wen, Hsio-Yi Lin, An-Pin Chen, and Chyan Yang An Integrated Home Financial Investment Learning Environment to Exploit Cloud Computing for Social Network Analysis Session D2: (Workshop) The First Workshop on Social Network Analysis in Applications (I) Room 419 Session Chair: Prof. Jason Jung 1. Qinna Wang and Eric Fleury Community Detection with Fuzzy Community Structure 2. Krzysztof Juszczyszyn, Marcin Budka and Katarzyna Musia The Dynamic Structural Patterns of Social Networks Based on Triad Transitions 3. Dipankar Das and Sivaji Bandyopadhyay Emotions on Bengali Blog Texts: Role of Holder and Topic 4. Anna Zygmunt, Piotr Brdka, Przemyslaw Kazienko and Jarosaw Kolak Different Approaches to Groups and Key Person Identification in Blogosphere Session D3: Community Discovery and Analysis (II) Room 420 Session Chair: Prof. Nasrullah Memon 1. Freddy Chong Tat Chua and Ee-Peng Lim Modeling Bipartite Graphs Using Hierarchical Structures 2. Fergal Reid, Aaron Mcdaid and Neil Hurley Partitioning Breaks Communities
31
3.
12:00-13:30 13:30-14:30
14:30-14:50 14:50-16:50
Liang-Cheng Huang, Tso-Jung Yen and Seng-Cho T. Chou Community Detection in Dynamic Social Networks: A Random Walk Approach 4. Ting-Lin Lee and In-Chen Tu The Way of Joining Consortia Leads to a Good Performance - A Case of Taiwan Bike Industry 5. Qi Ye, Bin Wu, Zhixiong Zhao and Bai Wang Detecting Link Communities in Massive Networks Session D4: Temporal Analysis on Social Network Topologies Room 422 Session Chair: Prof. Edgar Fuller 1. Chi Wang, Jie Tang, Jimeng Sun and Jiawei Han Dynamic Social Influence Analysis through Time-dependent Factor Graphs 2. Bo Yang, Jing Huang, and Dayou Liu A Random Network Ensemble Model Based Generalized Network Communities Mining Algorithm 3. Chung-Hong Lee, Hsin-Chang Yang, Tzan-Feng Chien and Wei-Shiang Wen A Novel Approach for Event Detection by Mining Spatio-temporal Information on Microblogs 4. Michele Berlingerio, Michele Coscia, Fosca Giannotti, Anna Monreale and Dino Pedreschi Foundations of Multidimensional Network Analysis 5. Michele Berlingerio, Michele Coscia and Fosca Giannotti Finding and Characterizing Communities in Multidimensional Networks Lunch (Room 102, 103, 104) Keynote Speech 6 (Room B101) Chair: Prof. Ambuj K. Singh Professor Ming-Syan Chen, Director, Research Center for Information Technology Innovation, Academia Sinica, Taiwan Title: Information Processing in Social Networks Coffee Break (Room 102, 103, 104) Parallel Sessions E Session E1: Application of SNA Room 418 Sesion Chair: Prof. Tansel zyer 1. Han-Chang Huang and Hung-Yu Kao CAIS: Community based Annotation Insight Search in a Folksonomy Network 2. Xiao Yu, Ang Pan, Lu-An Tang, Zhenhui Li, and Jiawei Han Geo-Friends Recommendation in GPS-based Cyber-Physical Social Network 3. Chen Liang, Sharath Hiremagalore, Angelos Stavrou and Huzefa Rangwala Predicting Network Response Times Using Social Information 4. Min-Feng Wang, Sie-Long Jheng, Meng-Feng Tsai and Cheng-Hsien Tang Enterprise Email Classification Based on Social Network Features 5. Onur Can Sert, Kayhan Dursun, and Tansel zyer
32
Ensemble of Multi-Objective Clustering Unified With H-Confidence Metric as Validity Metric Session E2: Misbehavior and Crime Detection Room 419 Session Chair: Dr. M. Saravanan 1. Jenq-Haur Wang and Ming-Sheng Lin Using Inter-Comment Similarity for Comment Spam Detection in Chinese Blogs 2. Ruaylong Lee, Roozbeh Nia, Jason Hsu, Karl N. Levitt, Jeff Rowe, S. Felix Wu, and Shaozhi Ye Design and Implementation of FAITH, An Experimental System to Intercept and Manipulate Online Social Informatics 3. Fatih Ozgul, Claus Atzenbeck and Zeki Erdem How much Similar are Terrorists Networks of Istanbul? 4. M. Atif Qureshi, Arjumand Younus, Nasir Touheed, M. Shahid Qureshi, and Muhammad Saeed Discovering Irrelevance in the Blogosphere through Blog Search 5. Sarwat Nizamani, Nasrullah Memon, Uffe Kock Wiil and Panagiotis Karampelas CCM: A Text Classification Method by Clustering 6. Koji Maruhashi, Fan Guo and Christos Faloutsos MultiAspectForensics: Pattern Mining on Large-scale Heterogeneous Networks with Tensor Analysis Session E3: (Workshop) The 3rd International Workshop on Mining Social Networks for Decision Support Room 420 Session Chair: Prof. Yuan-Chu Hwang 1. I-Mei Lin and Yuan-Chu Hwang Exploring the Social Network Relationships on Hostility Behaviors 2. Pei-Shan Jang, I-Hsien Ting and Shyue-Liang Wang Towards Social Recommendation System Based on The Data from Microblogs 3. Yi-Ning Tu and Jia-Lang Seng Evaluating the Impact Power of Authors via Bayesian Estimation of Authors Social Connections 4. Chen-Shu Wang, I-Hsien Ting and Yu-Chieh Li Taiwan Academic Network Discussion via Social Networks Analysis Perspective 5. Qin Wu, Robert Duval, Edgar Fuller, Xingqin Qi, Cun-Quan Zhang, Arian Spahiu, and Kyle Christensen Modeling Network Changes: Systemic Centrality in Foreign Policy Interaction Analysis 6. Sreedhar Bhukya Discover Academic Experts in Novel Social Network Model Session E4: (Workshop) The First Workshop on Social Network Analysis in Applications (II) Room 422 Session Chair: Prof. Przemyslaw Kazienko 1. Krzysztof Jdrzejewski and Mikoaj Morzy
33
16:50-17:10 17:10-17:40
Opinion Mining and Social Networks: a Promising Match 2. Fang-Ling Lin and Guey-Fa Chiou Social Brokerage behind Knowledge Sharing 3. Wei-Lun Chang and Sian-Ting Lin Analyzing Personality Correlation of Social Network in Organizations 4. Arjumand Younus, M. Atif Qureshi, Fiza Fatima Asar, Muhammad Azam, Muhammad Saeed, and Nasir Touheed What do the Average Twitterers Say: a Twitter Model for Public Opinion Analysis in the Face of Major Political Events Coffee Break (Room 102, 103, 104) Closing Session (Room B101)
34
Conference Abstracts
ASONAM 2011
Session A1
10:50-12:30 Chair: Title Authors Abstract
Contextual Social Network Analysis (I)

July 25 (Monday) Prof. Georgios Lappas Room: 418
The ML-model for Multi-Layer Social Networks

Matteo Magnani and Luca Rossi In this paper we introduce a new model to represent and study an interconnected network of networks. This model is fundamental to reason about the real organization of on line social networks, where users belong to and interact on different networks at the same time. In addition we extend traditional SNA measures to deal with the multiplicity of networks and we present an empirical validation of the model.
Title Authors Abstract
Tag-based User Topic Discovery using Twitter Lists

Yuto Yamaguchi, Toshiyuki Amagasa, and Hiroyuki Kitagawa In this paper, we address the problem of tagging users in Twitter, one of the most popular micro-blogging services. There are growing needs to get useful information from Twitter, because an enormous amount of information is transmitted in real time. Twitter users, who play an important role as information sources, typically transmit information about some particular topics which they are interested in. Therefore, to identify useful information, it is very important to know which topics a user tends to transmit. In this paper, we propose a method to discover appropriate topics for a user by using Twitter list. Twitter list is an official functionality to make a user list, list members tend to transmit information about the topic represented in the name of the list. From this observation, our idea is to extract tags from list names, and exploit the relationship among lists, tags extracted from the list names, and list members. Experimental results show the effectiveness of the proposed method.
Content-based Modeling and Prediction of Information Dissemination

Kathy Macropol and Ambuj Singh Social and communication networks across the world generate vast amounts of graph-like data each day. The modeling and prediction of how these communication structures evolve can be highly useful for many applications. Previous research in this area has focused largely on using past graph structure to predict future links. However, a useful observation is that many graph datasets have additional information associated with them beyond just their graph structure. In particular, communication
35
graphs (such as email, twitter, blog graphs, etc.) have information content associated with their graph edges. In this paper we examine the link between information content and graph structure, proposing a new graph modeling approach, GC-Model, which combines both. We then apply this model to multiple real world communication graphs, demonstrating that the built models can be used effectively to predict future graph structure and information flow. On average, GC-Models top predictions covered 19% more of the actual future graph communication structure when compared to other previously introduced algorithms, far outperforming multiple link prediction methods and several naive approaches. Title Authors Abstract
SCENE: Structural Conversation Evolution NEtwork

Marina Danilevsky, Joshua Hailpern, and Jiawei Han Its not just what you say, but it is how you say it. To date, the majority of the Instant Message (IM) analysis and research has focused on the content of the conversation. The main research question has been, what do people talk about? focusing on topic extraction and topic modeling. While content is clearly critical for many real-world applications, we have largely ignored identifying how people communicate. Conversation structure and communication patterns provide deep insight into how conversations evolve, and how the content is shared. Motivated by theoretical work from psychology and linguistics in the area of conversation alignment, we introduce SCENE, an evolution network approach to extract knowledge from a conversation network. We demonstrate the potential of our approach by taking the task of matching conversation partners. We find that SCENE is more successful because, in contrast to existing approaches, SCENE treats a conversation as an evolving, rather than a static document, and focuses on the structural elements of the conversation instead of being tied to the specific content.
Title
A Hybrid Approach to Discover MEC Interview Data - With the Hierarchical Value Map of Social Networking Sites as an Example
Yu-Chin Liu, Ti-Lin Chueh, and Yun-Shan Cheng As the booming of social network sites (SNSs), people adapt to communicate and share information via internet recently. According to great business opportunities emerging in SNSs, entrepreneurs strive to explore the potential needs inside users and then provide interesting feature functions on SNS platforms. The Means-End Chain (MECs) research method has been widely used to explore customers perceived values in selecting products [1]. It is a good approach to help entrepreneurs finding the most appreciated product features. But however, while adopting MECs, researchers suffer the hassle of defining Attribute, Consequence and Value elements (ACV elements) from interview data. In addition, such context analyzing work heavily relies on researchers subjective opinions, so that the research conclusions might be difficult to replicate and the contributions are limited. Therefore, this paper aims to propose hybrid miming techniques to automatically discover Attribute, Consequence and Value elements which are the most essential
Authors Abstract
36
components in MEC approach. A case on studying customers perceived values of social network cites is conducted by the proposed hybrid approach, and the experimental results show our method can discover the ACV elements effectively
Session A2
Scalability in Social Network Analysis

July 25 (Monday) Prof. Nitesh Chawla Room: 419
DisNet: A Framework for Distributed Graph Computation

Ryan N. Lichtenwalter and Nitesh V. Chawla With the rise of network science as an exciting interdisciplinary research topic, efficient graph algorithms are in high demand. Problematically, many such algorithms measuring important properties of networks have asymptotic lower bounds that are quadratic, cubic, or higher in the number of vertices. For analysis of social networks, transportation networks, communication networks, and a host of others, computation is intractable. In these networks computation in serial fashion requires years or even decades. Fortunately, these same computational problems are often naturally parallel. We present here the design and implementation of a master-worker framework for easily computing such results in these circumstances. The user needs only to supply two small fragments of code describing the fundamental kernel of the computation. The framework automatically divides and distributes the workload and manages completion using an arbitrary number of heterogeneous computational resources. In practice, we have used thousands of machines and observed commensurate speedups. Writing only 31 lines of standard C++ code, we computed betweenness centrality on a network of 4.7M nodes in 25 hours.
Automatic Tag Attachment Scheme for Efficient File Search in Peer-to-Peer File Sharing Systems
Ting Ting Qin and Satoshi Fujita In this paper, we consider the problem of automatic tag attachment to the documents distributed over a P2P network aiming at improving the efficiency of file search in such networks. The proposed scheme combines text clustering with a modified tag extraction algorithm, and is executed in a fully distributed manner. We conducted experiments to evaluate the accuracy of the proposed scheme. The result of experiments indicates that for more than 90% of documents, it attaches the same tags as the ones attached by human reviewers.
Probabilistic Subgraph Matching on Huge Social Networks

Matthias Broecheler, Andrea Pugliese, and V.S. Subrahmanian Users querying massive social networks or RDF databases are often not 100% certain about what they are looking for due to the complexity of the query or heterogeneity of the data. In this paper, we propose probabilistic subgraph (PS) queries over a graph/network database, which afford users
37
great flexibility in specifying approximately what they are looking for. We formally define the probability that a substitution satisfies a PS-query with respect to a graph database. We then present the PMATCH algorithm to answer such queries and prove its correctness. Our experimental evaluation demonstrates that PMATCH is efficient and scales to massive social networks with over a billion edges. Title Authors Abstract
Shortest Path Discovery in the Multi-layered Social Network

Piotr Brdka, Pawe Stawiak, and Przemyslaw Kazienko Multi-layered social networks consist of the fixed set of nodes linked by multiple connections. These connections may be derived from different types of user activities logged in the IT system. To calculate any structural measures for multi-layered networks this multitude of relations should be coped with in the parameterized way. Two separate algorithms for evaluation of shortest paths in the multi-layered social network are proposed in the paper. The first one is based on pre-processing aggregation of multiple links into single multi-layered edges, whereas in the second approach, many edges are processed on the fly in the middle of path discovery. Experimental studies carried out on the DBLP database are presented as well.
Discovering Explorative Patterns from Real World Complex Networks

Bo Yang and Jiming Liu The ability to discover patterns of networks is fundamental for structural analysis applied to them. Many ubiquitous patterns demonstrated by real-world networks have been discovered, and corresponding tools for finding them also have been developed. Although existing works have greatly improved our understanding on networks, it is still challenging to precisely model and predict their behaviors mainly because their non-trivial structures usually consists of manyfold coexisting patterns which cannot be appropriately and totally uncovered by a single tool exclusively designed for pre-defined ones. In this work, we take an effort to address this issue by introducing a parameter-free algorithm aiming to discover such patterns hidden in an explorative network.
Session A3
(Workshop) The First International Workshop on Mobile Social Network
10:50-12:30 Chair: Title Authors
July 25 (Monday) Dr. Kun-Lung Wu
Room: 420
GPS Data Based Urban Guidance

Yao-Hua Ho, Yao-Chuan Wu, Meng Chang Chen, Tsun-Jui Wen, and Yeali S. Sun
38
Abstract
In many metropolitan areas, traffic congestion is an escalating problem which causes a significant waste of money and time. Nowadays, cars equipped with GPS devices become widespread. The location information of those cars is very useful for estimate traffic condition in the complex city road network. Using the accurate and real time traffic condition, we can provide dynamic route guidance to ease traffic congestion. In this paper, we proposed a speed pattern model, called two phase piecewise linear speed model (2PEED), to estimate traffic condition and represent speed pattern in a road network using GPS data collected vehicles. With the estimated traffic condition and speed pattern, a proposed classification-based route guidance approach using machine learning technique provides dynamic routing for drivers. Using both current traffic data and the experience learned from history data, our route guidance approach is able to accurately predict the future traffic condition and selects a best route. We give simulation results to show that the proposed approach is able to select and dynamically update a route to prove drivers a best (e.g., less traffic and shortest travel time) route to their destination.
A Framework of Recommendation System Based on both Network Structure and Messages

Bi-Ru Dai, Chang-Yi Lee, and Chih-Heng Chung The evolving of Internet technology allows people to communicate even they are far away from each other. More and more people share information and exchange their thoughts via the communities on the websites and become friends. A larger community usually attracts more users, therefore, how to enhance the development of a social network on the website is an important issue for the survival of a website. In this paper, we combine the social network features into the recommendation system. In addition to messages between nodes, the features of network structure are taken into consideration. Experimental results show that the recommendation accuracy of our method is higher than the existing method which is based on the message ratio.
Bayesian Filters for Mobile Recommender Systems

M. Saravanan, S. Buveneswari, S. Divya, and V. Ramya With millions of registered users and a phenomenal increase in the amount of information exchange between them, it is clear that social networks are becoming increasingly popular on the Internet. Due to this popularity, they have become an important platform for business and marketing activities. In this paper, we understand the availability and the need of social networking sites with the mobile environment. The existing mobile recommender systems focus on targeting the users based on predicted demographics rather than the interests of the user. By extracting users information from social networking sites, we design four novel lters to improve the targeting accuracy of the mobile service providers. Finally we have applied the Bayesian approach on the lters to arrive at a proper response percentage of the targeted customers. In essence, we ensure that based on applied strategy of understanding the customer's unique preferences, mobile service providers can launch specific
39
campaigns on selected groups of users to get useful feedback. Moreover, it improves customer loyalty towards the operator. We have evaluated our ndings through standard techniques on real world data. Title Authors Abstract
Assessing Media Relevance via Eye Tracking

Cheng-Ta Yang, Wen-Sheng Chang, Fan-Ning Cheng, and Wei-Guang Teng To ease the problem of data overloading, it is crucial to understand the user behavior when s/he interacts with online contents, or more specifically, a web page containing several entries for further exploration. We devise to estimate the relevance of an entry to the user goal by observing eye movements as implicit feedback. Specifically, this study proposes a framework that assumes eye movement measures can be used to infer a users cognition. A rating task was conducted in which subjects were required to judge whether an image was relevant to a word. Results showed that the total fixation duration and the fixation count can be used to discriminate between the relevant and irrelevant conditions; in contrast, the first fixation duration cannot. In addition, the subjective rating and relevancy manipulation interacted on the total fixation duration. Converging evidence verifies the assumption we have proposed.
Mobile Engagement
Jianhua Shao Web of Things is a practice towards Internet of Things. It enables physical digital objects to be organised as web resources. Mobility enables mobile phones as a great media to engage people with operations to those extended web resources in Web of Things. Mobile engagements include three scopes with differences on networking and purposing. We illustrate each engagement with specific examples. Each engagement could complement each other to improve overall performance. In practice, apps are the actual implementations for mobile engagement. Meanwhile, privacy control of digital footprint needs to be explored further for mobile engagement because of data explosion in the Web of Things.
Session A4
Information Acquisition and Establishment of Social Networks
July 25 (Monday) Prof. Chien-Hsing Wu
Room: 422
Extracting Social Networks to Understand Interaction

Mathilde Forestier, Julien Velcin, and Djamel A. Zighed Web forums are a huge data source. They allow people to interact with unknown individuals. Studying forums shows that the interaction is not obvious only through the structure but also through the content of the post. Taking into account this observation, we extract a social network with different kinds of relationships i.e. the structural relation, the name
40
and the text quotations relation. We present here the promising results we obtain, and the difficulties we face while extracting the quotations in this kind of textual content. These results are obtained from real data (from two information websites) which make the validation difficult. So, we create a validation protocol composed of two steps and based on human raters. Finally, we will see the objective of this work which is understanding interactions in order to extract the social roles of individuals. Title Authors Abstract
Entity Resolution using Social Graphs for Business Applications

Baoshi Yan, Lokesh Bajaj and, Anmol Bhasin Social network such as LinkedIn maintains profiles for its members in a semi-structured format. A lot of business applications like ad targeting and content recommendations rely on canonicalization of data elements like companies, titles and schools for enabling fine grained advertising or recommending candidates for job postings. In this paper we explore the issues around resolving company names for hundreds of millions of member positions to known company entities using the social graph. We proposed a machine learning approach leveraging three dimensional feature sets including the social graph, social behavior and various content and demographic features. The experiments showed that our approach achieved high precision at a reasonable coverage and is significantly superior to a baseline content based approach.
SNAP: Towards a Validation of the Social Network Assembly Pipeline

Michael Farrugia, Neil Hurely, and Aaron Quigley A key problem for social network analysis is the lack of ground-truth data upon which to validate an analysis. Consider for example community-finding algorithms. The communities identified by such algorithms are typically justified on the basis of their structural properties, rather than on their ability to recover communities which can be independently verified. A ground truth of actual community data isnt always available and at best only partial ground-truth community information is. However, this problem isnt unique to community-finding algorithms. In previous publications, we introduced an automated Social Network Assembly Pipeline we refer to as SNAP. This is intended for the large scale actor identification, tie interference and strength measurement of social networks from non-relational data sets. In this paper we describe a validation study of SNAP through an intensive user-study of a portion of the individuals in the network. Individuals are asked to validate the network relationships uncovered by SNAP and where misclassified relationships are found, the individuals are interviewed in order to determine the underlying cause of the misclassification. The findings provide feedback on the rules through which relationships are inferred. For instance, it becomes clear that an error in actor identification can result in a propagation of this error though the network relations leading to follow-on relationship misclassifications. Also, we observe how outliers lead to a propagation of error in the inferred network. The results help us
41
validate and invalidate different hypotheses we have about SNAP and suggests domain specific rule-sets for SNAP. Title Authors Abstract
Dyadic Patterns in Multiple Networks

Antonio Rivero Ostoic Seven dyadic configuration classes for the analysis of multiple networks are introduced in this paper. Each configuration is a relational bundle pattern resulting from the mixture of the direction and the types of tie between a pair of actors. Then a bundle census is performed to an empirical network made of three kinds of relations, and the algorithm used for the bundle class detection is presented with a generalization of networks up to r types of tie.
Session B1
Recommendation (I)
July 25 (Monday) Dr. Johann Stan Room: 418
Co-Author Relationship Prediction in Heterogeneous Bibliographic Networks

Yizhou Sun, Rick Barber, Manish Gupta, Charu Aggarwal, and Jiawei Han The problem of predicting links or interactions between objects in a network, is an important task in network analysis. Along this line, link prediction between co-authors in a co-author network is a frequently studied problem. In most of these studies, authors are considered in a homogeneous network, i.e., only one type of objects (author type) and one type of links (co-authorship) exist in the network. However, in a real bibliographic network, there are multiple types of objects (e.g., venues, topics, papers) and multiple types of links among these objects. In this paper, we study the problem of co-author relationship prediction in the heterogeneous bibliographic network, and a new methodology called PathPredict, i.e., meta path-based relationship prediction model, is proposed to solve this problem. First, meta path-based topological features are systematically extracted from the network. Then, a supervised model is used to learn the best weights associated with different topological features in deciding the co-author relationships. We present experiments on a real bibliographic network, the DBLP network, which show that meta path-based heterogeneous topological features can generate more accurate prediction results as compared to homogeneous topological features. In addition, the level of significance of each topological feature can be learned from the model, which is helpful in understanding the mechanism behind the relationship building.
Regularized Gibbs Sampling for User Profiling with Soft Constraints

Nicola Barbieri In this paper we extend the formulation of the User Rating Profile model, providing a Gibbs Sampling derivation for parameter estimation.
42
Validation tests on Movielens data show that the proposed approach outperforms significantly the variational version in terms of both prediction accuracy and learning time. Gibbs Sampling provides a simple and flexible learning procedure which can be extended to include external evidence, in the form of soft constraints. More specifically, given apriori information about user-neighbors, we propose an effective regularization technique that drives the first sampling iterations pushing the model towards a state which better represents the user-neighborhoods specified in input. Title Authors Abstract
A Recommendation Method for Online Dating networks based on Social Relations and Demographic Information
Lin Chen, Richi Nayak, and Yue Xu A new relationship type of social networks - online dating - are gaining popularity. With a large member base, users of a dating network are overloaded with choices about their ideal partners. Recommendation methods can be utilized to overcome this problem. However, traditional recommendation methods do not work effectively for online dating networks where the dataset is sparse and large, and a two-way matching is required. This paper applies social networking concepts to solve the problem of developing a recommendation method for online dating networks. We propose a method by using clustering, SimRank and adapted SimRank algorithms to recommend matching candidates. Empirical results show that the proposed method can achieve nearly double the performance of the traditional collaborative filtering and common neighbor methods of recommendation.
Applying Multidimensional Association Rule Mining to Feedback-based Recommendation Systems

Yin-Fu Huang and San-Des Lin The main characteristic of collaborative filtering is to provide personalized recommendations to a customer based on the customer profile, without considering content information about domain items. In this paper, we investigated to use a relevance feedback mechanism in the collaborative recommendation system. First, we used the Self-organizing Map (SOM) method to avoid suffering from the scalability and sparsity problem in the collaborative filtering. In addition, we adopted the Statistical Attribute Distance (SAD) method which uses the similarity in statistics of customers ratings to calculate customer correlations, instead of using the statistics of customers that rate for similar items. Then, the multi-tier granule mining algorithm was used to find association rules. Finally, with the relevance feedback mechanism and the association rules, the recommendations could be refined to provide customers more relevance information.
Identifying Structural Heterogeneities Between Online Social Networks For Effective Word-of-Mouth Marketing
Kai-Yu Wang, Narongsak Thongpapanl, Hui-Ju Wu, and I-Hsien Ting Social networks are extremely important for word-ofmouth (WOM)
43
marketing. However, marketers often ignore network structures when developing WOM marketing strategies. Specifically, there is clearly a lack of research on looking into overall structures and structural heterogeneities of social networks. This research investigates structural heterogeneities between online social networks in different product categories. We collected data from four online networks in different product categories from the most popular social networking site in Taiwan. Social network analysis was performed to understand the network structures. The findings demonstrate the structural heterogeneities between these networks and we also provide managerial implications for practitioners. Title Authors Abstract
Multiword Keyword Recommendation System for Online Advertising

Stamatina Thomaidou and Michalis Vazirgiannis As search engines, social networks, and the World Wide Web become more popular and widely used, online advertising turns into a very profitable industry. Individuals and companies promote their products or services in search engines through textual ads, alongside the organic search results triggered by a specific query. For this purpose, advertisers must create advertising campaigns. The development of these campaigns is a laborious task involving significant human resources and expertise. In this paper we propose a system for multiword keyword recommendations in the context of developing a web advertising campaign in a semiautomatic manner. Given a landing page, the system extracts relevant terms consisted of two or three words to match a potential search query. Furthermore, it proposes the most relevant keywords and other suggested terms that do not exist in the landing page text using search result snippets. In addition, we present blind testing experiments on real world data indicating that our approach outperforms prominent existing industrial solutions in most of the cases.
Session B2
Privacy and Security

July 25 (Monday) Prof. Guido Barbian Room: 419
Social Network Anonymization via Edge Addition

Bruce Kapron, Gautam Srivastava, and S. Venkatesh The growing need to address privacy concerns when social network data is released for mining purposes has recently led to considerable interest in various techniques for graph anonymization. In this paper, we study the following problem: Given a social network modeled as an edge-labeled graph G, we aim to make a pre-specified subset of vertices of G k-label sequence anonymous with the minimum number of edge additions. Here, the label sequence of a vertex is the sequence of labels of edges incident to it. The contributions of this paper are two fold: We provide a framework to show hardness results for different variants of social network
44
anonymization using a common approach. We start by showing that k-label sequence anonymity of arbitrary labeled graphs is hard, and use this result to prove NP-hardness results for many other recently proposed notions of graph anonymization. Secondly, we present interesting algorithms and hardness for bipartite graphs. For unlabeled bipartite graphs, we show k-degree anonymity is in P for all k 2. For labeled bipartite graphs, we show that k-label sequence anonymity is in P for k = 2 but it is NP-hard for k 3. Title Authors Abstract
Assessing Trust by Disclosure in Online Social Networks

Guido Barbian Knowing about trust between members of an online social network (OSN) is essential for many applications. In this paper we propose and discuss methods for deriving information about trust within a social network by analyzing disclosure of personal information items. A formal model of trust and disclosure is presented and possible trust functions were analysed. We distinguish different types of information and assess their privacy value. A methodology for calculating privacy values and trust functions is provided.
Locating Central Actors in Co-offending Networks

Mohammad A. Tayebi, Laurens Bakker, Uwe Glsser, and Vahid Dabbaghian A co-offending network is a network of offenders who have committed crimes together. Recently different researches have shown that there is a fairly strong concept of network among offenders. Analyzing these networks can help law enforcement agencies in designing more effective strategies for crime prevention and reduction. One of the important tasks in co-offending network analysis is central actors identification. In this paper, firstly we introduce a data model, called unified crime data model to bridge the conceptual gap between abstract crime data level and co-offending network mining level. Using this data model, we extract the co-offending network of five years real-world crime data. Then we apply different variations of centrality methods on the extracted network and discuss how key player identification and removal can help law enforcement agencies in policy making for crime reduction.
Social Network Privacy for Attribute Disclosure Attacks

Sean Chester and Gautam Srivastava Increasing research on social networks stresses the urgency for producing effective means of ensuring user privacy. Represented ubiquitously as graphs, social networks have a myriad of recently developed techniques to prevent identity disclosure, but the equally important attribute disclosure attacks have been neglected. To address this gap, we introduce an approach to anonymize social networks that have labeled nodes, proximity, which requires that the label distribution in every neighbourhood of the graph be close to that throughout the entire network. We present an effective greedy algorithm to achieve -proximity and experimentally validate the quality of the solutions it derives.
45
Post-Level Spam Detection for Social Bookmarking Web Sites

Hsin-Chang Yang and Chung-Hong Lee Social bookmarking Web sites have emerged recently for collecting and sharing of interesting Web sites among users. People can add Web pages to such sites as bookmarks and allow themselves as well as others to manipulate them. One of the key features of the social bookmarking sites is the ability of annotating a Web page when it is being bookmarked. The annotation usually contains a set of words or phrases, which are collectively known as tags, that could reveal the semantics of the annotated Web page. Efficient and effective search of Web pages can then be achieved via such tags. However, spam tags that are irrelevant to the content of Web pages often appear to deceive other users for malicious or commercial purposes. Various techniques have been devised to tackle such tag spam detection problem. Most of these techniques were able to detect a user that always annotates spam tags. However, finer levels of detection are seldom discussed. In this work, we will propose a method based on a text mining approach to discover the relations between Web pages and there tag posts. These relations are then used to compute the similarity between a Web page and its tag post to decide if it is a spam post. Preliminary experiments show that the accuracy of the post-level spam detection task is 83%.
Mining Information of Anonymous User on a Social Network Service

Kyung Soo Cho, Jae Yoel Yoon, Iee Joon Kim, Ji Yeon Lim, Seung Kwan Kim, and Ung-Mo Kim The growing number of individuals is recently writing their own opinions or information freely at the network space on the web such as the blog or Online Cafe and these network spaces are developed toward a new service called social network. Consequently, a lot of researchers are studying this social network lively. The social network is not only a tool for providing real time news, but also having an effect on an opinion or a policy decision. It uses mainly texts to present information in real-time, and its users use a computer or a mobile device to upload their own opinions or ideas. A lot of texts from users contain important and various information. We will get this information we need real-time if semantic can be extracted from texts on a social network. In this case, Opinion mining should be useful to extract semantic from social network. This paper suggests a noble method to grasp information of anonymous users through relationship information available and their psychology that is reflected on texts and also understand the meanings of contents in depth.
Session B3
15:20-17:20 Chair:
Dynamic Social Networks (I)

July 25 (Monday) Prof. Yu-Hui Tao Room: 420
46
Multi-Relational Link Prediction in Heterogeneous Information Networks

Darcy Davis, Ryan Lichtenwalter, and Nitesh V. Chawla Many important real-world systems, modeled naturally as complex networks, have heterogeneous interactions and complicated dependency structures. Link prediction in such networks must model the influences between heterogeneous relationships and distinguish the formation mechanisms of each link type, a task which is beyond the simple topological features commonly used to score potential links. In this paper, we introduce a novel probabilistically weighted extension of the Adamic/Adar measure for heterogeneous information networks, which we use to demonstrate the potential benefits of diverse evidence, particularly in cases where homogeneous relationships are very sparse. However, we also expose some fundamental flaws of traditional a priori link prediction. In accordance with previous research on homogeneous networks, we further demonstrate that a supervised approach to link prediction can enhance performance and is easily extended to the heterogeneous case. Finally, we present results on three diverse, real-world heterogeneous information networks and discuss the trends and tradeoffs of supervised and unsupervised link prediction in a multi-relational setting.
Social Network User Lifetime

Juan Lang and S. Felix Wu Online Social Network (OSN) operators are interested in promoting usage among their users, and try a variety of strategies to encourage use. Some recruit celebrities to their site, some allow third parties to develop applications that run on their sites, and all have features intended to encourage use. As important as usage is, we are unaware of any studies into what influences users to be active and to remain online. This paper is the first work studying the lifetime of OSN users, examining the factors that influence lifetime in one OSN, Buzznet. The major contributions of this work are the study of active lifetime, the features and behaviors that encourage activity, and the comparison of active lifetime to passive lifetime.
Predicting Social Network Structure once a Node is Deleted

Elsa Negre, Rokia Missaoui, and Jean Vaillancourt Social networks are dynamic structures in which entities and links appear and disappear for different reasons. Starting from the observation that each entity has a more or less important role within the network, the objective of this article is to propose a method which exploits the role played by nodes to predict the new structure of a social network once one entity disappears. The role of a node in the network is expressed in terms of the number of interactions it has with the rest of the network. Two roles are considered: the leader and the mediator with their corresponding measure: the degree centrality and the betweenness
47
centrality. Title Authors Abstract
A New Analysis Method for Simulations Using Node Categorizations

Tomoyuki Yuasa and Susumu Shirayama Most research concerning the influence of network structure on phenomena taking place on the network focus on relationships between global statistics of the network structure and characteristic properties of those phenomena, even though local structure has a significant effect on the dynamics of some phenomena. In the present paper, we propose a new analysis method for phenomena on networks based on a categorization of nodes. First, local statistics such as the average path length and the clustering coefficient for a node are calculated and assigned to the respective node. Then, the nodes are categorized using the self-organizing map (SOM) algorithm. Characteristic properties of the phenomena of interest are visualized for each category of nodes. The validity of our method is demonstrated using the results of two simulation models.
Dynamics of Adolescent Friendships: The Interplay between Structure and Gender

Pei-Chun Ko and Vincent Buskens This study investigates the network characteristics of adolescent friendship networks and the interaction between network characteristics and gender. Two competing hypotheses for closure and openness are derived and tested. Adolescents might strive for network closure, because this facilitates trust and trustworthiness among their friends. However, openness can also be beneficial because it facilitates establishing multi-layered identities and finding novel ideas for school tasks. The hypothesis for interaction between structure and gender is derived from the argument that gender influences the criteria for seeking and making friends during adolescence. SIENA is used to estimate the effects of network and individual characteristics on friendship formation. The data consists of longitudinal friendship nominations of 410 Taiwanese adolescents. We find that adolescents have a tendency to establish friendships that increase network closure. This tendency is stronger for male than for female adolescents in single-gender classes. On the contrary, the tendency towards network closure is stronger for female than for male adolescents in mixedgender classes.
Information Sources Driving Social Influence: A New Model for Belief Learning in Social Networks
Usha Sridhar and Sridhar Mandyam Non-Bayesian models for learning in social networks, such as the DeGroot model, are focused on updating beliefs using social influence weights, and study the achievement of convergence of beliefs to a consensus. In this paper, we propose a new construct to capture the notion of agents using additional information sources, such as media, to obtain multiple affirmations of belief information through an
48
information score. We use this new construct to create a feedback learning loop that allows agents to learn beliefs with social influences varying dynamically with the credibility of the information on such beliefs. We build a new social learning mechanism, without the constraining rowstochasticity assumptions on social influence, and show that with information sources driving social influences, the beliefs can converge, and not necessarily to a consensus, even with strong connectivity. In this process of learning agents with a similar alignment between exogenous information sources and beliefs group together, and this reflects in the structure of social influences. The results of the new learning algorithm are demonstrated on a small, fully connected social network.
Session B4
(Workshop) Cyberpsychological Analysis of Social Network Analysis in Applications

July 25 (Monday) Prof. Shiro Uesugi Room: 422
Effects of Personality Traits on Usage of Social Networking Service

Shiro Uesugi A number of social networking services (SNSs) have become increasingly popular in recent years, as characterized by the growing number of their users and the deepening penetration of their services. As the number of users increases, the variety of user profiles, serving as a reflection of the real world, also increases. Psychological aspects must be taken into account to better understand the behaviors of SNS users. This study investigated the relationships between personality traits and SNS usage, and the results of a preliminary survey using the Big Five model of personality traits are reported herein.
Title
The Moderating Role of Virtual Community Cohesion and Critical Mass on the Link between Online-Game Website Service Quality and Play Satisfaction
Yu-Lung Wu, Yu-Hui Tao, Ching-Pu Lee, Pei-Chi Yang, and Guo-Shin Huang The online game market in Taiwan is close to saturation. The sudden emergence of online community games has lead to a change in the type of game players, and online game providers are forced to deploy new strategies to cope with this change in trend. Meanwhile, literature research reveals a mixed result of the impact of virtual community cohesion and critical mass on online game platform service quality and satisfaction. Therefore, this research further investigates the moderating roles of online players virtual community cohesion and critical mass on the link between website service quality and player satisfaction. The result indicates that virtual community cohesion does play a moderating
Authors Abstract
49
role while critical mass does not. Discussions and implications are also provided in this paper. Title
Encouraging Participation in Virtual Community with Classified Facilitation Mechanisms: A Perspective from Online Communication Needs and Behaviors
M.C. Chang and S.D. Gregor Based on a literature review and three focused group sessions involving a total of 30 experienced designers of virtual community, this research examines design principles of computer-mediated facilitation mechanisms from the perspective of meeting participants online communication needs. The design principles are classified into three categories based on members intrapersonal, interpersonal and group communication needs and behaviors. The findings address the importance of understanding the different communication needs for individual participants when selecting facilitation mechanisms to encourage member participation in virtual communities. These findings yield innovative implications for research and practice.
Authors Abstract
Reconceptualizing the Internet Human Flesh Search Mechanism: Review of the Literature
Chian-Hsueng Chao The development of Internet technologies and popularity of social network enable the netizens to search, process, broadcast, and share information in a more efficient and collaborative way. Opinions of netizens in the cyberspace have emerged and become one of the major public opinions in the real world. One of the phenomenon rising recently over the Internet that most represent the influence between the virtual and real world is human flesh search (HFS). Usually, the HFS object is incompatible with social justice or violation of the mainstream moral characters, or events. This violation of moral triggers the HFS process either in the cyberspace or in the real world. HFS has arose numerous controversies, especially the dilemmas between privacy violation and public opinion. Literatures and studies of HSF are mainly from China. International journals or periodical literatures target on this issue are very few. In addition, current studies are mainly qualitative studies lacking of quantitative and theoretical model building and empirical research. Therefore, it is necessary to acquire better understanding of HSF structure and evolving process. The purpose of this paper is to provide a broad discussion and summarized attributes of HFS. Based on reviews of more than twenty journal papers and articles regarding HFS, this study hopes to formulate a reference framework for future HFS studies.
Title
The Organizational Justice Strategies to Affect Learning Performance and Self-efficacy : A Case study in Campus Media News Gathering
Chia Sung Yen, Shih Chun Yang, Tien Hui Yeh, and Yi Inn Sun It is important to perform teamwork with high organizational justice. When some unfair events happen, it is counterproductive not only to the
Authors Abstract
50
performance of the organization, but to organizational efficacy as well. Presses are time-conscious organizations, but they have to face the difficulty of resource distribution. The main purpose of this study is to examine organizational justice in presses. Because presses are so different from other organizations, there must be some kinds of important elements composing their organizational justice. In the procedure of news gathering, reporters always have to face the uncertainty of those events. If presses emphasize too much on the equity of distribution, it is possible that they may miss the deadline, or even lose the news. So presses seem to need another kind of evaluation to appraise their organizational justice. This paper would focus on the campus media, finding how students perform when they face the assignments of news gathering, and what strategies to do justice in this media could affect students self-efficacy. Title
A Comparison of Cognitive Styles on the Behavior of Obtaining Knowledge: Field Independence vs. Field Dependence
Chienhsing Wu, Shuchen Kao, Jiwe Chang, and Kaeying Chen This paper compares the cognitive style of field independence/dependence (FI, FD) on the behavior of obtaining knowledge from online learning system. The process of obtaining knowledge is considered with respect to the involvement of knowledge provider s and receiver s cognition characteristics. The experiment is conducted where two groups with FI for one and FD for another are arranged. Data analysis results indicate that (1) FI group spends more time on the designed KO than FD does. For non-designed KO, contrarily, the FD group has more time spent than FI group. (2) FI style is more likely to acquire knowledge from internal sources while FD prefers external where they can perform social interactions as the primary means to acquire knowledge. (3) FI group is likely monotonous to stick firmly with common or preferred passive knowledge resources; on the other hand, the learning process of FD group seems to be more varied, and often passing through in-between several different knowledge sources. Discussion and implications are also addressed.
Authors Abstract
Session C1
Contextual Social Network Analysis (II)

July 26 (Tuesday) Prof. Chung-Hong Lee Room: 418
Efficient Search in Networks Using Conductance

Qing Ke, Yuxiao Dong, and Bin Wu Decentralized search in networks is an important algorithmic problem in the study of complex networks and social networks analysis. It has a large number of practical applications, from shortest paths search in social network relationship, web pages search in WWW to querying files in peer-to-peer file sharing networks and so on. In this paper, we explore
51
this problem from a perspective of community structure. We first find that through maximizing sample conductance, we can get high coverage sample. Based on this result, then, we propose a new decentralized search strategy named Conductance Search which tries to efficiently find the nodes belonging to different communities. We compare the strategy with other common strategies. And the results show that the conductance search outperforms others in number of steps to find the target and time complexity. Finally, we find some previous conclusions fail in many real-world networks and discuss network search-ability from the perspective of various structural properties. Title Authors Abstract
A Semantic and Multidisciplinary Model for Professional and Social Networks Analysis
Christophe Thovex and Francky Trichet By bridge-building between the classical models of social networks analysis, ontologies engineering and physics, our work defines a multidisciplinary model of professional social networks analysis, dedicated to human and social capital management in enterprises and institutions. We introduce a semantic process of social graphs static and dynamic analysis, based on the enterprise content and producing decisional tools for the performance management. This approach is in line with the SOCIOPRISE project, in partnership with a leader software engineering company for human capital management. SOCIOPRISE is funded by the French State Secretariat at the prospective and development of digital economy.
Visualizing Bibliographic Databases as Graphs and Mining Potential Research Synergies

Iraklis Varlamis and George Tsatsaronis Bibliographic databases are a prosperous field for data mining research and social network analysis. They contain rich information, which can be analyzed across different dimensions (e.g., author, year, venue, topic) and can be exploited in multiple ways. The representation and visualization of bibliographic databases as graphs and the application of data mining techniques can help us uncover interesting knowledge concerning potential synergies between researchers, possible matchings between researchers and venues, or even the ideal venue for presenting a research work. In this paper, we propose a novel representation model for bibliographic data, which combines coauthorship and content similarity information, and allows for the formation of scientific networks. Using a graph visualization tool from the biological domain, we are able to provide comprehensive visualizations that help us uncover hidden relations between authors and suggest potential synergies between researchers or groups.
SPOT 1.0 : Scoring Suspicious Profiles on Twitter

Charles Perez, Marc Lemercier, Babiga Birregah, and Alain Corpel Everyday more than fifty million messages are generated by about two hundred million profiles on Twitter. Some users attempt to exploit the
52
success of this microblogging platform and its relative freedom to perform malicious actions that can lead to identity or data theft. This work aims to propose a framework to assess suspicious behavior on Twitter. We present a tool developed for Scoring Suspicious Profiles On Twitter (SPOT 1.0) through a threedimensional indicator that involves the degree of aggressiveness, the visibility and the level of danger. Title Authors Abstract
Link Prediction Based on Local Information

Yuxiao Dong, Qing Ke, Bai Wang, and Bin Wu Link prediction in complex networks is an important issue in graph mining. It aims at estimating the likelihood of the existence of links between nodes by the know network structure information. Currently, most link prediction algorithms based on local information consider only the individual characteristics of common neighbors. In this paper, first, we study the link prediction results as the change of the exponent on the degree of common neighbors, and find some regular pattern between different networks and different exponent. After that, we come up with a new algorithm exploiting the interactions between common neighbors, namely Individual Attraction Index. To reduce the time complexity, we design a simple edition, called Simple Individual Attraction Index. We compare nine wellknown local information metrics on eight real networks. The result proves well the best overall performance of these two new algorithms.
Session C2 Recommendation (II)

10:20-12:00 Chair: Title Authors Abstract July 26 (Tuesday) Porf. Chen-shu Wang Room: 419
Modeling and Learning Context-Aware Recommendation Scenarios Using Tensor Decomposition

Hendrik Wermser, Achim Rettinger and Volker Tresp The task of recommending items, like movies, to users is a core feature of many social networks. Standard approaches either use item or user similarity to suggest the next items users might be interested in. Recently, multivariate models like matrix factorization have become popular to combine the advantages of both perspectives. In addition, extensions have been proposed to capture the dynamics of user interests over time, like trends or recurrent user needs. While offering good predictive performance, so far those models do not exploit possibly available rich semantic context. Typically, only one implicit feature, like user ratings, is tracked to give personalized recommendations. However, with semantic data sources, like linked data, wealthy background knowledge becomes available that could be leveraged to improve predictive performance. We argue, that a more flexible framework is needed to model and learn a greater class of recommendation scenarios where rich context is available. Thus, we propose a generic approach which generalizes state-of-the-art methods based on pairwise interaction tensor factorization by leveraging arbitrary background knowledge related to the recommendation
53
situation. Our experiments on streamed semantic data from a social network show that by adding varying sets of context - like user information, sequential information or time information - the ranking of potential items can be personalized and the predictive performance can be improved. Title Authors Abstract
Applying Link Prediction to Ranking Candidates for High-Level Government Post

Jyi-Shane Liu and Ke-Chih Ning The main focus of this study is the computational evaluation of candidacy for an executive vacancy. We identified a new problem framework on bureaucratic promotion and proposed to tackle the problem with social network analysis that involved bipartite graph and link prediction. A bureaucratic career bipartite network model was developed to encode key information reflecting a candidates service merit and the aggregated merit standards of an executive position. This allowed us to approximate merit measurement with node similarity. We implemented this candidacy evaluation approach and conducted experiments with data from Taiwans bureaucratic career database. Empirical evaluation shows acceptable baseline performance and demonstrates feasibility of the link prediction approach to candidacy ranking. The results also seem to indicate that bureaucratic promotion for executive positions in Taiwan government is mostly a merit system, as opposed to at-will.
Leveraging Online Social Networks and External Data Sources to Predict Personality
Daniel Chapsky Over the past decade, people have been expressing more and more of their personalities online. Online social networks such as Facebook.com capture much of individuals personalities through their published interests, attributes and social interactions. Knowledge of an individuals personality can be of wide utility, either for social research, targeted marketing or a variety of other fields A key problem to predicting and utilizing personality information is the myriad of ways it is expressed across various people, locations and cultures. Similarly, a model predicting personality based on online data which cannot be extrapolated to real world situations is of limited utility for researchers. This paper presents initial work done on generating a probabilistic model of personality which uses representations of peoples connections to other people, places, cultures, and ideas, as expressed through Facebook. To this end, personality was predicted using a machine learning method known as a Bayesian Network. The model was trained using Facebook data combined with external data sources to allow further inference. The results of this paper present one predictive model of personality that this project has produced. This model demonstrates the potential of this methodology in two ways: First, it is able to explain up to 56% of all variation in a personality trait from a sample of 615 individuals. Second it is able to clearly present how this variability is explained through findings such as how to determine how agreeable a man is based on his age,
54
number of Facebook wall posts, and his willingness to disclose his preference for music made by Lady Gaga. Title Authors Abstract
Semantic User Interaction Profiles for Better People Recommendation

Johann Stan, Viet-Hung Do and Pierre Maret In this paper we present a methodology for learning user profiles from content shared by people on Social Platforms. Such profiles are specifically tailored to reflect the users degree of interactivity related to the topics they are writing about. The main novelty in our work is the introduction of Linked Data in the content extraction process and the definition of specific scores to measure expertise and interactivity.
Title
Modeling Player Performance in Massively Multiplayer Online Role-Playing Games: The Effects of Diversity in Mentoring Network
Kyong Jin Shim, Kuo-Wei Hsu, and Jaideep Srivastava This study investigates and reports preliminary findings on player performance prediction approaches which model player's past performance and social diversity in mentoring network in EverQuest II, a popular massively multiplayer online role-playing game (MMORPG) developed by Sony Online Entertainment. Our contributions include a better understanding of performance metrics used in the game and a foundation of recommendation systems for mentors and apprentices. We examined three different game servers from the EverQuest II game logs. In all three servers, the results from our analyses suggest that increase in social diversity in terms of characters and classes encountered moderately negatively correlates with player performance. Based on this finding, we built predictive models to predict player's future performance based on past performance and social diversity in terms of mentoring activities. Our results indicate that 1) models employing past performance and social diversity perform better and 2) prediction for mentors is generally better than that for apprentices.
Authors Abstract
Session C3
Dynamic Social Networks (II)

July 26 (Tuesday) Dr. Mi-Yen Yeh Room: 420
Modeling and Visualizing Information Propagation in a Micro-blogging Platform

Chien-Tung Ho, Cheng-Te Li, and Shou-De Lin Micro-blogging is a type of social networking service that has become ubiquitous in Web 2.0 era. Micro-blogs allows bloggers to exchange information, discuss ideas, and share experiences with friends or even strangers with similar interests. In this paper, we try to identify ways to measure how information is propagated in micro-blogs. More specifically, we consider the following issues. (1) How to quantify a
55
persons capability to disseminate ideas via a micro-blog. (2) How to measure the extent of propagation of a concept in a micro-blog. (3) How to demonstrate and visualize information propagation in a microblog. We propose methods to effectively measure each users ability to disseminate information via micro-blogs. The design of the measure considers three factors: (a) the number of people influenced; (b) the speed of propagation; and (c) the geographic distance of the propagation. We also provide an online demonstration micro-blog system that allows the users to explore the information propagation. The system shows the propagation paths and social graphs, influence scores, timelines, and geographical information among people for the user-given terms. Title Authors Abstract
From Web Mining to Social Multimedia Mining

Georgios Lappas Web mining is a well established field with many applications. Over the last years we experience a vast and rapidly growing amount of multimedia content that becomes available online. Web 2.0 and online social networks have dramatically influenced the growing amount of multimedia content due to the fact that users become more active producers and distributors of such multimedia context. Web mining techniques and theory need to be expanded in order to include new emerging research trends from mining such heterogeneous new web data. This work conceptualizes and introduces the concept of social multimedia mining as a new emerging research area that combines web mining research, multimedia research and social media research.
Modeling Socialness in Dynamic Social Networks

Tuan-Anh Hoang, Ee-Peng Lim, Palakorn Achananuparp, Jing Jiang, and Loo-Nin Teow Socialness refers to the ability to elicit social interaction and social links among people. It is a concept often associated with individuals. Although there are tangible benefits in socialness, there is little research in its modeling. In this paper, we study socialness as a property that can be associated with items, beyond its traditional association with people. We aim to model an items socialness as a quantitative measure based on the how popular the item is adopted by members of multiple communities. We propose two socialness models, namely Basic and Mutual Dependency, to compute item socialness based on different sets of principles. In developing the Mutual Dependency Model, we demonstrate that items socialness can be related to the socialness of communities. Our model have been evaluated on a set of users and application items from a mobile social network. We also conducted experiments to study how socialness can be related to network effects such as homophily, social influence and friendship formation.
Title
Rank Prediction in graphs with Locally Weighted Polynomial Regression and EM of Polynomial Mixture Models
Michalis Rallis and Michalis Vazirgiannis
Authors
56
Abstract
In this paper we describe a learning framework enabling ranking predictions for graph nodes based solely on individual local historical data. The two learning algorithms capitalize on the multi feature vectors of nodes in graphs that evolve in time. In the first case we use weighted polynomial regression (LWPR) while in the second we consider the Expectation Maximization (EM) algorithm to fit a mixture of polynomial regression models. The first method uses separate weighted polynomial regression models for each web page, while the second algorithm capitalizes on group behavior, thus taking advantage of the possible interdependence between web pages. The prediction quality is quantified as the similarity between the predicted and the actual rankings and compared to alternative baseline predictor. We performed extensive experiments on a real world data set (the Wikipedia graph). The results are very encouraging.
Time Scale Degree Centrality: A Time-Variant Approach to Degree Centrality Measures

Shahadat Uddin and Liaquat Hossain In this paper, we introduce a time-variant approach to degree centrality measure - time scale degree centrality (TSDC), which considers both presence and duration of links among actors within a network; whereas, the traditional degree centrality approach regards only the presence or absence of links. We illustrate the difference between traditional and time scale degree centrality measure by applying these two approaches to explore the impact of degree attributes of doctor-patient network that evolves during patient hospitalization period on the hospital length of stay (LOS) both in macro- and micro-level. In macro-level, both the traditional and time-scale approaches to degree centrality can explain the relationship between the degree attribute of doctor-patient network and LOS. However, at micro-level or small cluster level, TSDC provides better explanation while traditional degree centrality approach is impotent to explain the relationship between them.
Session C4 Community Discovery and Analysis (I)

10:20-12:00 Chair: Title Authors Abstract July 26 (Tuesday) Prof. Hsin-Chang Yang Room: 422
Evolutionary Clustering and Analysis of Bibliographic Networks

Manish Gupta, Charu C. Aggarwal, Jiawei Han, and Yizhou Sun In this paper, we study the problem of evolutionary clustering of multi-typed objects in a heterogeneous bibliographic network. The traditional methods of homogeneous clustering methods do not result in a good typed-clustering. The design of heterogeneous methods for clustering can help us better understand the evolution of each of the types apart from the evolution of the network as a whole. In fact, the problem of clustering and evolution diagnosis are closely related because
57
of the ability of the clustering process to summarize the network and provide insights into the changes in the objects over time. We present such a tightly integrated method for clustering and evolution diagnosis of heterogeneous bibliographic information networks. We present an algorithm, ENetClus, which performs such an agglomerative evolutionary clustering which is able to show variations in the clusters over time with a temporal smoothness approach. Previous work on clustering networks is either based on homogeneous graphs with evolution, or it does not account for evolution in the process of clustering heterogeneous networks. This paper provides the first framework for evolutionsensitive clustering and diagnosis of heterogeneous information networks. The ENetClus algorithm generates consistent typedclusterings across time, which can be used for further evolution diagnosis and insights. The framework of the algorithm is specifically designed in order to facilitate insights about the evolution process. We use this technique in order to provide novel insights about bibliographic information networks. Title Authors Abstract
Group Evolution Discovery in Social Networks

Piotr Brdka, Stanisaw Saganowski, and Przemyslaw Kazienko Group extraction and their evolution are among the topics which arouse the greatest interest in the domain of social network analysis. However, while the grouping methods in social networks are developed very dynamically, the methods of group evolution discovery and analysis are still uncharted territory on the social network analysis map. Therefore the new method for the group evolution discovery called GED is proposed in this paper. Additionally, the results of the first experiments on the email based social network together with comparison with two other methods of group evolution discovery are presented.
Finding and Matching Communities in Social Networks Using Data Mining

Slah Alsaleh, Richi Nayak and Yue Xu The rapid growth in the number of users using social networks and the information that a social network requires about their users make the traditional matching systems insufficiently adept at matching users within social networks. This paper introduces the use of clustering to form communities of users and, then, uses these communities to generate matches. Forming communities within a social network helps to reduce the number of users that the matching system needs to consider, and helps to overcome other problems from which social networks suffer, such as the absence of user activities information about a new user. The proposed system has been evaluated on a dataset obtained from an online dating website. Empirical analysis shows that accuracy of the matching process is increased using the community information.
Evaluating Cooperation in Communities with the k-core Structure

Christos Giatsidis, Dimitrios M. Thilikos, and Michalis Vazirgiannis Community subgraphs are characterized by dense connections or
58
interactions among its nodes. Community detection and evaluation is an important task in graph mining. A variety of measures have been proposed to evaluate the quality of such communities. In this paper, we evaluate communities based on the k-core concept, as means of evaluating their collaborative nature - a property not captured by the single node metrics or by the established community evaluation metrics. Based on the k-core, which essentially measures the robustness of a community under degeneracy, we extend it to weighted graphs, devising a novel concept of k-cores on weighted graphs. We applied the kcore approach on large real world graphs such as DBLP and report interesting results. Title Authors Abstract
Is Objective Function the Silver Bullet? A Case Study of Community Detection Algorithms on Social Networks
Yang Yang, Yizhou Sun, Saurav Pandit, Nitesh V. Chawla, and Jiawei Han Community detection or cluster detection in networks is a well-studied, albeit hard, problem. Given the scale and complexity of modern day social networks, detecting reasonable communities is an even harder problem. Since the first use of k-means algorithm in 1960s, many community detection algorithms have been invented - most of which are developed with specific goals in mind and the idea of detecting meaningful communities varies widely from one algorithm to another. With the increasing number of community detection algorithms, there has been an advent of a number of evaluation measures and objective functions such as modularity and internal density. In this paper we divide methods of measurements in to two categories, according to whether they rely on ground-truth or not. Our work is aiming to answer whether these general used objective functions are well consistent with the real performance of community detection algorithms across a number of homogeneous and heterogeneous networks. Seven representative algorithms are compared under various performance metrics, and on various real world social networks.
Session D1 (Workshop) The 1st International Workshop on Cloud Computing in Social Networks
10:20-12:00 Chair: Title Authors Abstract July 27 (Wednesday) Dr. Wen-Chih Tsai Room: 418
Constructing a Cloud Computing Based Social Networks Data Warehousing and Analyzing System
I-Hsien Ting, Chia-Hung Lin, and Chen-Shu Wang The research area of Social networks analysis has been recognized as extremely time-consuming tasks as well as large storage space is always necessary in order to store the social data, especially to deal with the data in the World Wide Web. Therefore, how to design an architecture and
59
environment for performing social networks analysis is very essential. In this paper, we proposed a data warehousing and analyzing system which is based on the concept of cloud computing. The system has also been implemented and evaluated under the proposed environment with different cloud computing approaches. Title Authors Abstract
Cloud Computing Architecture for Social Computing A Comparison Study of Facebook and Google
Bo-Wen Yang, Wen-Chih Tsai, An-Pin Chen, and Singh Ramandeep As far as we know, cloud computing is a new business model and the cloud computing architecture is the famous topic recently. Today, everyone enjoy the innovative search engine or social network application for new Internet services no longer require the large capital outlays in hardware to access those service or the human expense to operate it. Currently, Google is the largest search engine and Facebook is the largest social network in the Software as a Service (SaaS). But how them can support the huge requests from world thought each personal computer, mobile device, and smart phone. In this paper, we will try to analysis their backend cloud computing architecture to support future SaaS especially in large social network.
Building a Learning Games Network in Cloud Learning Platform based on Immigrant Education
Chien-Chih Tu and An-Pin Chen As with rapid growth of the computer technology, Elearning systems usually require many hardware and software resources, There are numerous educational institutions that cannot offer such investments, and cloud learning platform is the best solution for them. This paper proposes a model of using cloud computing and learning network upon cloud-learning solutions development. The cloud-learning platform combined with different types of games is gradually noticed by people because it can enhance user learning motivation. This research has developed a Chinese language cloud-learning system for the new immigrant based on games mode, and investigated the properties of game-based cloud-learning system, expecting to help more and more new immigrants in Taiwan. The basic concept for designing the system is developing the learning games network using digital materials, which is applied to the cloud learning platform to attract the immigrant residents and assist them to improve Chinese language skills.
Title
An Integrated Home Financial Investment Learning Environment to Exploit Cloud Computing for Social Network Analysis
Mao-Ping Wen, Hsio-Yi Lin, An-Pin Chen, and Chyan Yang This paper tried to apply cloud computing technology in social network analysis for a comprehensive home financial learning environment that individual investors may use as a reference in establishing web-based learning and investment platforms. The major contributions were described in three parts. First, this paper advanced the social network
Authors Abstract
60
analysis technology to be able to handle millions of nodes and links. Second, we demonstrate how cloud computing can be applied to advanced computing in social network. Third, we performed several intelligent analyses on a very popular social network, IHFILE, to identify some interesting and important features of it. In addition to analyzing a homogeneous social network such as IHFILE, we also propose direction of how cloud computing can be performed on a social network analysis as our future work.
Session D2 (Workshop) The First Workshop on Social Network Analysis in Applications (I)
10:20-12:00 Chair: Title Authors Abstract July 27 (Wednesday) Prof. Jason Jung Room: 419
Community Detection with Fuzzy Community Structure

Qinna Wang and Eric Fleury In order to find a cover which allows nodes to be shared among several communities, we propose a simple fuzzy community detection algorithm, which is based on an existing partition detection technique. For the performance of overlapping nodes that makes the partition ambiguous, a new extended modularity is introduced to qualify covers. With modularity optimization, the cover can be found with a high quality. We applied our method to real networks. The results demonstrate that our method can discover meaningful fuzzy community structure, overlapping community structure and hierarchical structure.
The Dynamic Structural Patterns of Social Networks Based on Triad Transitions

Krzysztof Juszczyszyn, Marcin Budka, and Katarzyna Musia In modern social networks built from the data collected in various computer systems we observe constant changes corresponding to external events or the evolution of underlying organizations. In this work we present a new approach to the description and quantifying evolutionary patterns of social networks illustrated with the data from the Enron email dataset. We propose the discovery of local network connection patterns (in this case: triads of nodes), measuring their transitions during network evolution and present the preliminary results of this approach. We define the Triad Transition Matrix (TTM) containing the probabilities of transitions between triads, then we show how it can help to discover the dynamic patterns of network evolution. Also, we analyse the roles performed by different triads in the network evolution by the creation of triad transition graph built from the TTM, which allows us to characterize the tendencies of structural changes in the investigated network. The future applications of our approach are also proposed and discussed.
Title
Emotions on Bengali Blog Texts: Role of Holder and Topic
61
Authors Abstract
Dipankar Das and Sivaji Bandyopadhyay The paper presents an approach to identify the emotions of the bloggers on different topics provided in the Bengali blog documents. The rule based identification of emotion holders and topics along with their corresponding emotional expressions forms the baseline system. A Support Vector Machine (SVM) based supervised framework is also employed to identify the three components from the blog sentences and it outperforms the baseline system. As the topic of a document is not always conveyed at the sentence level, the similarity between a documents overall topic and sentential topic is measured through semantic clustering approach. Two different approaches are adopted to identify the many to many relationships among the holders and topics on Ekmans six emotions. One is based from the perspectives of the holders and other is with respect to topics. The two way evaluation of Ekmans six emotions achieves precision, recall and F-Score of 65.02%, 76.23% and 70.18% for 10 bloggers and 71.02%, 78.47% and 74.55% for 8 different topics on 512 test sentences respectively.
Different Approaches to Groups and Key Person Identification in Blogosphere

Anna Zygmunt, Piotr Brdka, Przemyslaw Kazienko and Jarosaw Kolak Two approaches for identifying key persons in the blogosphere-based social network are analysed in the paper: discovery of the most important individuals either in persistent or in global social communities existing on web blogs. A new method for the separation of stable groups fulfilling given conditions is presented. Additionally, a new concept for extraction of user roles and key persons in such groups is proposed. It has been compared to the general clustering method and structural node position measure applied to rank users in the time-aggregated data. Experimental, comparative studies have been conducted on real blogosphere data gathered over one year.
Session D3 Community Discovery and Analysis (II)

10:20-12:00 Chair: Title Authors Abstract July 27 (Wednesday) Prof. Nasrullah Memon Room: 420
Modeling Bipartite Graphs Using Hierarchical Structures

Freddy Chong Tat Chua and Ee-Peng Lim Bipartite networks are often used to capture the relationships between different classes of objects. To model the structure of bipartite networks, we propose a new hierarchical model based on a hierarchical random graph model originally designed for one-mode networks [1]. The new model can better preserve the network fidelity as well as the assortative and disassortative structures of bipartite networks. We apply the proposed model on some paperauthor networks in DBLP to find their optimal hierarchical structures. Using the optimal bipartite hierarchical structure, we regenerate networks that exhibit the similar network
62
properties and degree distribution as the observed networks Title Authors Abstract
Partitioning Breaks Communities

Fergal Reid, Aaron Mcdaid, and Neil Hurley Considering a clique as a conservative definition of community structure, we examine how graph partitioning algorithms interact with cliques. Many popular community-finding algorithms partition the entire graph into non-overlapping communities. We show that on a wide range of empirical networks, from different domains, significant numbers of cliques are split across separate partitions, as produced by such algorithms. We examine the largest connected component of the subgraph formed by retaining only edges in cliques, and apply partitioning strategies that explicitly minimise the number of cliques split. We conclude that, due to the connectedness of many networks, any community finding algorithm that produces partitions must fail to find at least some significant structures. Moreover, contrary to traditional intuition, in some empirical networks, strong ties and cliques frequently do cross community boundaries.
Community Detection in Dynamic Social Networks: A Random Walk Approach

Liang-Cheng Huang, Tso-Jung Yen and Seng-Cho T. Chou This study aims to tackling community detection problems in dynamic social networks. The main approach focuses on exploring the idea of random walk in formulating modularity functions for community detection. Under this approach, a modularity function is defined as the difference between the probability of a Markov chain induced by a community and the probability of a null model that assumes no detectable community structure exists in the network. In this paper, we demonstrate the modularity-based approach by applying it to identify group boundaries in an adolescence friendship networks spanning a period of five months. Results and future directions will be discussed.
The Way of Joining Consortia leads to a good performance : A Case of Taiwan Bike Industry
Ting-Lin Lee and In-Chen Tu This The article use visually social network analysis (SNA) to present networking activities of Taiwans bike and components firms interacting in domestic market. The study uses data from questionnaires of sixty-five bike and component firms to explore the influence of organizational learning, relationship quality and network position on organizational performance. Results show that relationship quality positively affects organizational learning and organizational performance; and network position partially affects organizational performance. It is worth noted that a non-A-TEAM member (say IDEAL, coded GB_01) also had a higher in-degree and closeness centrality, and a better performance as well. Here is a key point to be re-thinking: is joining consortia the best way to lead a good performance? The answer is not fully supported by the case of Taiwans bike industry.
63
Detecting Link Communities in Massive Networks

Qi Ye, Bin Wu, Zhixiong Zhao, and Bai Wang In this paper, we study the problem of evolutionary clustering of multi-typed objects in a heterogeneous bibliographic network. The traditional methods of homogeneous clustering methods do not result in a good typed-clustering. The design of heterogeneous methods for clustering can help us better understand the evolution of each of the types apart from the evolution of the network as a whole. In fact, the problem of clustering and evolution diagnosis are closely related because of the ability of the clustering process to summarize the network and provide insights into the changes in the objects over time. We present such a tightly integrated method for clustering and evolution diagnosis of heterogeneous bibliographic information networks. We present an algorithm, ENetClus, which performs such an agglomerative evolutionary clustering which is able to show variations in the clusters over time with a temporal smoothness approach. Previous work on clustering networks is either based on homogeneous graphs with evolution, or it does not account for evolution in the process of clustering heterogeneous networks. This paper provides the first framework for evolutionsensitive clustering and diagnosis of heterogeneous information networks. The ENetClus algorithm generates consistent typedclusterings across time, which can be used for further evolution diagnosis and insights. The framework of the algorithm is specifically designed in order to facilitate insights about the evolution process. We use this technique in order to provide novel insights about bibliographic information networks.
Session D4 Temporal Analysis on Social Network Topologies

10:20-12:00 Chair: Title Authors Abstract July 27 (Wednesday) Prof. Edgar Fuller Room: 422
Dynamic Social Influence Analysis through Time-dependent Factor Graphs

Chi Wang, Jie Tang, Jimeng Sun, and Jiawei Han Social influence, the phenomenon that the actions of a user can induce her/his friends to behave in a similar way, plays a key role in many (online) social systems. For example, a company wants to market a new product through the effect of word of mouth in the social network. It wishes to find and convince a small number of influential users to adopt the product, and the goal is to trigger a large cascade of further adoptions. Fundamentally, we need to answer the following question: how to quantify the influence between two users in a large social network? To address this question, we propose a pairwise factor graph (PFG) model to model the social influence in social networks. An efficient algorithm is designed to learn the model and make inference. We further propose a dynamic factor graph (DFG) model to incorporate the time information.
64
Experimental results on three different genres of data sets show that the proposed approaches can efficiently infer the dynamic social influence. The results are applied to the influence maximization problem, which aims to find a small subset of nodes (users) in a social network that could max- imize the spread of influence. Experiments show that the proposed approach can facilitate the application. Title Authors Abstract
A Random Network Ensemble Model Based Generalized Network Community Mining Algorithm
Bo Yang, Jing Huang, and Dayou Liu The ability to discover community structures from explorative networks is useful for many applications. Most of the existing methods with regard to community mining are specifically designed for assortative networks, and some of them could be applied to address disassortative networks by means of intentionally modifying the objectives to be optimized. However, the types of the explorative networks are unknown beforehand. Consequently, it is difficult to determine what specific algorithms should be used to mine appropriate structures from exploratory networks. To address this issue, a novel concept, generalized community structure, has been proposed with the attempt to unify the two distinct counterparts in both types of networks. Furthermore, based on the proposed random network ensemble model, a generalized community mining algorithm, so called G-NCMA, has been proposed, which is promisingly suitable for both types of networks. Its performance has been rigorously tested, validated and compared with other related algorithms against real-world networks as well as synthetic networks. Experimental results show the G-NCMA algorithm is able to detect communities, without any prior, from explorative networks with a good accuracy.
A Novel Approach for Event Detection by Mining Spatio-temporal Information on Microblogs

Chung-Hong Lee, Hsin-Chang Yang, Tzan-Feng Chien, and Wei-Shiang Wen Social networks have been regarded as a timely and cost-effective source of spatio-temporal information for many fields of application. However, while some research groups have successfully developed topic detection methods from the text streams for a while, and even some popular microblogging services such as Twitter did provide information of top trending topics for selection, it is still unable to fully support users pickup all of the real-time event topics with a comprehensive spatiotemporal viewpoint to satisfy their information needs. This paper aims to enhance the understanding on how social networks can be used as a reliable source of spatio-temporal information, by analyzing the temporal and spatial dynamics of Twitter activity. In this work, we developed several algorithms for mining microblogging text stream to obtain real-time and geospatial event information. The goal of our approach is to effectively detecting and grouping emerging topics by making use of realtime messages and geolocation data provided by social network services.
Title
Foundations of Multidimensional Network Analysis
65
Authors Abstract
Michele Berlingerio, Michele Coscia, Fosca Giannotti, Anna Monreale and Dino Pedreschi Complex networks have been receiving increasing attention by the scientific community, thanks also to the increasing availability of real-world network data. In the last years, the multidimensional nature of many real world networks has been pointed out, i.e. many networks containing multiple connections between any pair of nodes have been analyzed. Despite the importance of analyzing this kind of networks was recognized by previous works, a complete framework for multidimensional network analysis is still missing. Such a framework would enable the analysts to study different phenomena, that can be either the generalization to the multidimensional setting of what happens in monodimensional network, or a new class of phenomena induced by the additional degree of complexity that multidimensionality provides in real networks. The aim of this paper is then to give the basis for multidimensional network analysis: we develop a solid repertoire of basic concepts and analytical measures, which takes into account the general structure of multidimensional networks. We tested our framework on a real world multidimensional network, showing the validity and the meaningfulness of the measures introduced, that are able to extract important, nonrandom, information about complex phenomena.
Finding and Characterizing Communities in Multidimensional Networks

Michele Berlingerio, Michele Coscia and Fosca Giannotti Complex networks have been receiving increasing attention by the scientific community, also due to the availability of massive network data from diverse domains. One problem studied so far in complex network analysis is Community Discovery, i.e. the detection of group of nodes densely connected, or highly related. However, one aspect of such networks has been disregarded so far: real networks are often multidimensional, i.e. many connections may reside between any two nodes, either to reflect different kinds of relationships, or to connect nodes by different values of the same type of tie. In this context, the problem of Community Discovery has to be redefined, taking into account multidimensionality. In this paper, we attempt to do so, by defining the problem in the multidimensional context, and by introducing also a new measure able to characterize the communities found. We then provide a complete framework for finding and characterizing multidimensional communities. Our experiments on real world multidimensional networks support the methodology proposed in this paper, and open the way for a new class of algorithms, aimed at capturing the multifaceted complexity of connections among nodes in a network.
Session E1
14:50-16:50
Application of SNA
July 27 (Wednesday) Room: 418
66
Chair: Title Authors Abstract
Prof. Tansel zyer
CAIS: Community based Annotation Insight Search in a Folksonomy Network

Han-Chang Huang and Hung-Yu Kao Folksonomy systems provide a way for users to share and organize bookmarks. The social relationship among users has become stronger with the rapid development of new technologies. Finding the leading objects has become an important topic. These research topics are always centered around finding the most popular pages or experts. In this paper, we propose a new notion of expertise, which we call user insight. User insight denotes the users expertise in finding Web pages that are useful or have the potential to be popular pages before other users find them. To address the issue, we refer to three major types of Web pages, namely, isolated, well-known, and burgeoning. Burgeoning pages are exceptionally useful and attractive for users in a folksonomy system. In our paper, we build a time-based algorithm to estimate user insight. In addition, we discuss the social relationship within fan networks, and we propose a link-based algorithm called CAIS (Community-based Annotation Insight Search) to realize the reinforcement between users, communities and pages. Finally, we design several experiments to evaluate the performance of CAIS and compare it to other approaches. We prove that CAIS has a better performance for the user ranking of simulated data and real data from Del.ici.ous.
Geo-Friends Recommendation in GPS-based Cyber-physical Social Network

Xiao Yu, Ang Pan, Lu-An Tang, Zhenhui Li, and Jiawei Han The popularization of GPS-enabled mobile devices provides social network researchers a taste of cyber-physical social network in advance. Traditional link prediction methods are designed to find friends solely relying on social network information. With location and trajectory data available, we can generate more accurate and geographically related results, and help web-based social service users find more friends in the real world. Aiming to recommend geographically related friends in social network, a three-step statistical recommendation approach is proposed for GPS-enabled cyber-physical social network. By combining GPS information and social network structures, we build a pattern-based heterogeneous information network. Links inside this network reflect both peoples geographical information, and their social relationships. Our approach estimates link relevance and finds promising geo-friends by employing a random walk process on the heterogeneous information network. Empirical studies from both synthetic datasets and reallife dataset demonstrate the power of merging GPS data and social graph structure, and suggest our method outperforms other methods for friends recommendation in GPS-based cyberphysical social network.
Title
Predicting Network Response Times Using Social Information
67
Authors Abstract
Chen Liang, Sharath Hiremagalore, Angelos Stavrou, and Huzefa Rangwala Social networks and discussion boards have become a significant outlet where people communicate and express their opinion freely. Although the social networks themselves are usually well-provisioned, the participating users frequently point to external links to substantiate their discussions. Unfortunately, the sudden heavy traffic load imposed on the external, linked web sites causes them to become unresponsive leading to the Flash Crowds effect. In this paper, we quantify the prevalence of flash crowd events for a popular social discussion board (Digg). We measured the response times of 1289 unique popular websites. We were able to verify that 89% of the popular URLs suffered variations in their response times. By analyzing the content and structure of the social discussions, we were able to forecast accurately for 86% of the popular web sites within 5 minutes of their submission and 95% of the sites when more (5 hours) of social content became available. Our work indicates that we can effectively leverage social activity to forecast network events that will be otherwise infeasible to anticipate.
Enterprise Email Classification Based on Social Network Features

Min-Feng Wang, Sie-Long Jheng, Meng-Feng Tsai and, Cheng-Hsien Tang With the popularity of multimedia and network technologies, it is now often to attach large size of multimedia dataset to emails. However, delivering large volume of multimedia data over an enterprise email system can easily bring down the quality of overall network service. Moreover, without some sort of restrictions, many enterprises found that the network resource was occupied for personal interests. The business communication over emails thus suffers undesirable delays and cause damages to businesses. The competition to use email service therefore become an issue that many enterprises have to deal with. Obviously, enterprises should manage the email service so that business emails have the priority over personal usages. This management requires an effective methodology to classify enterprise emails into official and private emails, and the development of the method is the goal of this work. To achieve the accuracy of a desired classification methodology, we normally anticipated the developed method to survey as much information as possible. On the other hand, monitoring details of the email contents not only can decrease the performance of the method, but it also may violate the privacy rights that many legal regulation systems now protect. The balance of pursuing accurate classification and protecting privacy rights becomes a challenge for this problem. With the discussed challenges in mind, we develop an email classification method based on social features, rather than surveying the email contents. To the best of our knowledge, this paper is the first study to address the aforementioned problems. We obtain social features from emails to represent the input vector of support vector machine (SVM) classifier. Preliminary results show that our methodology can classify emails with a high accuracy. Compared with the
68
other content-based feature of email, our work shows that exploring social features is a promising direction to solve similar email classification problems. Title Authors Abstract
Ensemble of Multi-Objective Clustering Unified With H-Confidence Metric as Validity Metric

Onur Can Sert, Kayhan Dursun, and Tansel zyer Multi objective clustering is one focused area of multi objective optimization. Multi objective optimization attracted many researchers in several areas over a decade. Utilizing multi objective clustering mainly considers multiple objectives simultaneously and results with several natural clustering solutions. Obtained result set suggests different point of views for solving the clustering problem. This paper assumes all potential solutions belong to different experts and in overall; ensemble of solutions finally has been utilized for finding the final natural clustering. We have tested on categorical, further on mixed credit card dataset with different objectives, and compared them against single objective clustering result in terms of purity.
Session E2
Misbehavior and Crime Detection

July 27 (Wednesday) Dr. M. Saravanan Room: 419
Using Inter-Comment Similarity for Comment Spam Detection in Chinese Blogs

Jenq-Haur Wang and Ming-Sheng Lin Blog has become one of the most popular ways of communication among social communities since blog posts can be replied, commented, and even shared to other users in a convenient way. All posts and comments, no matter good or bad, have to be manually coordinated by blog owners. In order to prevent comment spam, most blog sites provide challengeresponse tests such as CAPTCHA to ensure that the response is from human, instead of automatically generated by a computer. However, these tests cannot prohibit spammers from manually leaving spam messages. Existing studies of Chinese blog comment spam only focus on comments containing hyperlinks, which only stand for a small portion of blog comment spam. In this paper, we propose to include inter-comment Jaccard similarity in the features in addition to the post-comment similarity, stopwords ratio, and comment length for blog comment classification. In order to verify the effects of inter-comment similarity features, we compared several classification algorithms such as C4.5, Na Bayes, and Neural Network. Experimental results showed that the ve feature combination of inter-comment and postcomment similarity under the classification of C4.5 achieves the best performance. This shows the effectiveness of the proposed inter-comment similarity feature for Chinese blog comment spam classification.
Title
Design and Implementation of FAITH, An Experimental
69
System to Intercept and Manipulate Online Social Informatics

Authors Abstract Ruaylong Lee, Roozbeh Nia, Jason Hsu, Karl N. Levitt, Jeff Rowe, S. Felix Wu, and Shaozhi Ye Social informatics is the core of Facebooks business and is its most valuable asset which consists of the social graph and the private data of over 500 million users. However, without secure methods of managing this data, Facebook has become vulnerable to privacy risks and devaluation. In Facebooks model, users are asked upon access to grant applications the required permissions without sufficient knowledge of the applications intentions. As a result, if they are deceived, users risk the exposure of sensitive and personal data. This paper presents a system dubbed FAITH (Facebook Applications: Identification, Transformation & Hypervisor) to mitigate or eliminate these issues by enhancing the management of social data. First, FAITH allows users to adjust the visibility of their social informatics for each individual application depending on how much they trust the application. Users can configure FAITH to let non-trusted applications run with the least privileges (least amount of social informatics) to minimize potential privacy leaks. Second, FAITH logs the activities of applications to assist users in making more secure decisions. Users can closely monitor each activity performed by applications to adjust their privacy settings more securely. Third, FAITH allows users to transform their social graph such that different applications see different social graphs preventing the formation of friendship inflation caused by applications. The implementation of FAITH only needs the resources and tools available to the public by Facebook and requires no further cooperation from the social network. FAITH is a prototype system: the design and concept can be extended to secure other OSNs (Online Social Networks). Currently, FAITH contains thirteen Facebook social applications and has been officially released for public usage with approximately two hundred monthly active users as of now.
How Much Similar are Terrorists Networks of Istanbul?

Fatih Ozgul, Claus Atzenbeck, and Zeki Erdem Most of terrorist groups cooperate, interchange knowledge, skills and materials used for attacks. Terrorist groups in Istanbul are categorized into three main groups within criminological viewpoint: extreme left (i.e. Marxist) groups, extreme right (i.e. Fundamentalist, Radical Islamist) groups, and separatist (i.e. ethnic, racist) groups. Crime ontology for terrorist groups in Istanbul is created by using their criminal history and choices such as selection of crimes, attacking methods and modus operandi. Terrorist groups of Istanbul are attached to this ontology as nodes connected to their attacks. A similarity measure (COSM) is developed according to this ontology. COSM results for Istanbul terrorist groups performed better than two common similarity measures; cosine and Jaccard. COSM similarity result is presented to domain experts in hierarchical clustering and they gave positive feedback. COSM, which is based on attributes of crimes, can also be applied to other types of social
70
networks for measuring similarity. Title Authors Abstract
Discovering Irrelevance in the Blogosphere through Blog Search

M. Atif Qureshi, Arjumand Younus, Nasir Touheed, M. Shahid Qureshi, and Muhammad Saeed Web 2.0 technologies have given birth to the blogosphere, which is an information sharing medium by the users for the users. Furthermore, these technologies have also expanded the search problem to a new form of search known as blog search. Similar to Web search, blog search has been affected by spam which affects the quality of search results. This paper approaches the relevant blog problem in the top search results against the general topic queries. It pursues a study of irrelevant blogs appearing in the top search results of Google Blog Search for the blogspot domains. We define metrics for irrelevant blogs by observing the qualitative relevance of content and by analyzing the link structure of those blogs. Our preliminary results show an overall recall of 0.875 with a precision of 1.0 for finding irrelevant blogs in the top 15 search results against six general topic queries on Google Blog Search.
CCM: A Text Classification Model by Clustering

Sarwat Nizamani, Nasrullah Memon, Uffe Kock Wiil and Panagiotis Karampelas In this paper, a new Cluster based Classification Model (CCM) for suspicious email detection and other text classification tasks, is presented. Comparative experiments of the proposed model against traditional classification models and the boosting algorithm are also discussed. Experimental results show that the CCM outperforms traditional classification models as well as the boosting algorithm for the task of suspicious email detection on terrorism domain email dataset and topic categorization on the Reuters-21578 and 20 Newsgroups datasets. The overall finding is that applying a cluster based approach to text classification tasks simplifies the model and at the same time increases the accuracy.
MultiAspectForensics: Pattern Mining on Large-Scale Heterogeneous Networks with Tensor Analysis

Koji Maruhashi, Fan Guo, and Christos Faloutsos Modern applications such as web knowledge base, network traffic monitoring and online social networks have made available an unprecedented amount of network data with rich types of interactions carrying multiple attributes, for instance, port number and time tick in the case of network traffic. The design of algorithms to leverage this structured relationship with the power of computing to assist researchers and practitioners for better understanding, exploration and navigation of this space of information has become a challenging, albeit rewarding, topic in social network analysis and data mining. The constantly growing scale and enriching genres of network data always demand higher levels of efficiency, robustness and generalizability where existing approaches
71
with successes on small, homogeneous network data are likely to fall short. We introduce MultiAspectForensics, a handy tool to automatically detect and visualize novel subgraph patterns within a local community of nodes in a heterogenous network, such as a set of vertices that form a dense bipartite graph whose edges share exactly the same set of attributes. We apply the proposed method on three data sets from distinct application domains, present empirical results and discuss insights derived from these patterns discovered. Our algorithm, built on scalable tensor analysis procedures, captures spectral properties of network data and reveals informative signals for subsequent domain-specific study and investigation, such as suspicious port-scanning activities in the scenario of cybersecurity monitoring.
Session E3
(Workshop) The 3rd International Workshop on Mining Social Networks for Decision Support
July 27 (Wednesday) Prof. Yuan-Chu Hwang Room: 420
Exploring the Social Network Relationships on Hostility Behaviors

I-Mei Lin and Yuan-Chu Hwang How to determine who is the one that you are willing to express your emotion? Emotion expression and behavior responses are highly related to the subjective judgment of the target user, especially the negative emotions (e.g., anger/ hostility). This study is to explore how the hostility dimensions are distributed in various relationship types, including powerdependences, closeness distance, mutual expectations, and cooperation/competition. This study used semi-structured indepth interviews for a six-minute anger recall task that asked the participants to recall and report an anger event that happened in the past six months. There were 75 participants recruited to attend this study. The results indicate the dynamic social network types of power-dependences, closeness distance, and cooperation/competition are key factors to impact negative emotional behaviors and determine the hostility behaviors significantly. Although mutual expectations could also leads to higher anger level, but there is no significant difference on statistic analysis.
Towards Social Recommendation System Based on the Data from Microblogs

Pei-Shan Jang, I-Hsien Ting and Shyue-Liang Wang With the rapid growth of Internet and social networking websites, there are various services that provided in these platforms. For instance, Facebook focuses on social activities, Twitter and Plurk are both focus on the interaction of users through short messages (which are so-called microblogs). Therefore, there are more than millions of users registered
72
in these websites and become places where full of marketing possibilities. Thus, it is an important issue to assist companies to understand the users in the social networking websites in order to enhance the accuracy and efficiency of target marketing. In this paper, we have proposed the architecture of a social recommendation system based on the data from microblogs. The social recommendation system is conducted according to the messages and social structure of target users. The similarity of the discovered features of users and products will then be calculated as the essence of the recommendation engine. A case study will be included to present how the recommendation system works based on real data that collected from Plurk. Title Authors Abstract
Evaluating the Impact Power of Authors via Bayesian Estimation of Authors Social Connections
Yi-Ning Tu and Jia-Lang Seng This study tries to detect the impact research topics from impact authors with their connections, that is, who have larger impact in the same research field. These topics are impact research topics the pursuit of which would be very valuable for researchers, especially for new scholars or for researchers who want to combine their original field with other new domains but who may not have enough background knowledge about the new field. Bayesian estimation in our model uses subjective data (published volume) as the prior distribution and objective data as the likelihood function (citation frequency) to predict the posterior distribution of the target which we called impact power. After finding the impact power of each paper or topic then filtering these papers and topics, we can find impact research topics or papers.
Taiwan Academic Network Discussion via Social Networks Analysis Perspective

Chen-Shu Wang, I-Hsien Ting and Yu-Chieh Li Academic network (AN) is quite different network and hard to acquire relative information for inexperience researchers. To realize AN is an important but difficult work because of the constituents of AN are complicated and dynamic variation. In this research, two Taiwan academic networks are established from the perspectives of academic conference topic and participant committee. Each academic conference is regarded as an AN node to establish the conference academic network. In addition, there are two connection types between AN nodes, including: the relationship among CFP topics (academic conference topic perspective) and the relationship between committee member (participant committee perspective). Finally, 15 IT/IM relative target conferences in Taiwan 2009 are analyzed via social network analysis methodology. According to experiment result, the values of degree and betweeness reveal some interesting findings, such as TANET, OOTA and IMP are top three important bridge conferences in Taiwan. Additionally, as the cluster analyzed result shown, academic network somehow represents domain expertise because of the committee are grouped according to their research domains. These finding is consistence with the reality academic network in Taiwan and helpful information for
73
Taiwan academic network understanding. Title Authors Abstract
Modeling Network Changes: Systemic Centrality in Foreign Policy Interaction Analysis

Qin Wu, Robert Duval, Edgar Fuller, Xingqin Qi, Cun-Quan Zhang, Arian Spahiu, and Kyle Christensen The complex network of relationships between countries provides an abundance of data from which intelligence analysts must synthesize useful interpretations that effectively inform foreign policy and security decision making. In this work, a network of foreign policy event interactions is developed and then used to describe the state of the international system by estimating the behavioral distances from all relevant actors to the US. Using a graph theoretic approach, we develop a tool for estimating behavioral distances through direct network links when behavior is present, and indirect network paths when direct behavior is unobserved. The international system is examined in temporal aggregations of 60 and 30 days prior to and following the 1991 Gulf War and the 2003 invasion of Iraq. Both periods see distancing from the US as the wars approach, and a partial return to the prior state by 60 days after the initiation of conflict. The overall position of the US and the response of other nations towards the US indicates that the systemic leadership role of the US is diminished in behavioral relationships with a moderate number of actors.
Discover Academic Experts in Novel Social Network Model

Sreedhar Bhukya A number of recent studies on social networks are based on a characteristic which includes assortative mixing, high clustering, short average path lengths, broad degree distributions and the existence of community structure. Here, a model has been developed in the domain of Academic collaboration which satisfies all the above characteristics, based on some existing social network models. In addition, this model facilitates interaction between various communities (academic/research groups). This model gives very high clustering coefficient by retaining the asymptotically scale-free degree distribution. Here the community structure is raised from a mixture of random attachment and implicit preferential attachment. In addition to earlier works which only considered Neighbor of Initial Contact (NIC) as implicit preferential contact, we have considered Neighbor of Neighbor of Initial Contact (NNIC) also. This model supports the occurrence of a contact between two Initial contacts if the new vertex chooses more than one initial contacts. This ultimately will develop a complex social network rather than the one that was taken as basic reference.
Session E4
E4: (Workshop) The First Workshop on Social Network Analysis in Applications (II)
74
July 27 (Wednesday) Prof. Przemyslaw Kazienko
Room: 422
Opinion Mining and Social Networks: A Promising Match

Krzysztof Jdrzejewski and Mikoaj Morzy In this paper we discuss the role and importance of social networks as preferred environments for opinion mining and sentiment analysis especially. We begin by briefly describing selected properties of social networks that are relevant with respect to opinion mining and we outline the general relationships between the two disciplines. We present the related work and provide basic definitions used in opinion mining. Then, we introduce our original method of opinion classification and we test the presented algorithm on real world datasets acquired from popular Polish social networks, reporting on the results. The results are promising and soundly support the main thesis of the paper, namely, that social networks exhibit properties that make them very suitable for opinion mining activities.
Social Brokerage behind Knowledge Sharing

Fang-Ling Lin and Guey-Fa Chiou This study explored the implicit brokerage positions of social network behind knowledge sharing and demonstrated applicability to researches of community of practices. A concept of knowledge brokerage was proposed on the basis of the theory of social brokerage, and hypotheses were developed to verify the relational properties of brokerage opportunities. Social network analysis (SNA) was applied to conduct the egocentric network surveys and related analyses. Several new ways of evaluating the performance of knowledge sharing have been developed. The results verified the usability of brokerage as indicators of knowledge sharing. The results also can reveal efficiencies and deficiencies in knowledge dissemination among members of communities. These findings hold relevance for studies on the information technology practices of other professionals.
Analyzing Personality Correlation of Social Network in Organizations

Wei-Lun Chang and Sian-Ting Lin The focus of this study is to find out the similarity among personalities of persons. This study investigates 203 significant personality adjectives to find out the stable intrinsic value and the connotation of every adjective in context is introduced for vectorization comparison. The 203 phrases create 41209 similar scores totally. This study takes students of Tamkang University in Taiwan as subjects for establishing adjective database. The valid samples received are 973, the recovery rate being 83.87%. The following important conclusions are received after analysis, discussion and outcome induction: (1) In naturally formed interpersonal groups, openness to experience will be taken as the most important formative indicator. (2) Groups under high task environment will seek to take
75
conscientiousness as the primary formative indicator to converge into task groups. (3) Lover relationship takes partial personality similarity as the predominant phenomenon. The convergence of group personality will show comparatively obvious concentration. Title
What do the Average Twitterers Say: A Twitter Model for Public Opinion Analysis in the Face of Major Political Events
Arjumand Younus, M. Atif Qureshi, Fiza Fatima Asar, Muhammad Azam, Muhammad Saeed, and Nasir Touheed Social media platforms have become a forum for giving a voice to the masses with a significant proportion of those masses coming from the developing world. This was largely evidenced through the significant role played by social media platforms in the recent uprisings in the Arab world. In this paper, we take up a study of social media engagement patterns of users from the developing world through a study of Twitters role during the recent Tunisian uprising. Motivated by the results of a user survey conducted mainly for users from the developing world who tweeted heavily during the uprisings in the Arab world, we propose a novel method for subjectivity analysis of tweets corresponding to political events in the developing world. Our proposed method differs from previous subjectivity analysis approaches in that it is the first method that takes into account social features of social media platforms for the subjectivity classification task. Through experimental evaluations, we observe the accuracy of the proposed method to be 83.3% which demonstrates a promising outcome for large-scale application of our proposed subjectivity analysis technique.
Authors Abstract
76
Conference Posters
ASONAM 2011
Session
10:00-10:20 12:00-13:30 Chair: Title Authors Abstract
Poster
July 26 (Tuesday) Prof. Jeng-Shyang Pan Room: 101
Voting Behavior Analysis in the Election of Wikipedia Admins

Gerard Cabunducan, Ralph Castillo and John Boaz Lee Past work analyzing elections in online domains has largely ignored the underlying social networks present in such environments. Here, we study the Wikipedia Request for Adminship (RfA) process within the context of a social network and pinpoint several factors influencing different stages of the voting process. The facets explored are: election participation, decision making in elections, and election outcome. We find that voters tend to participate in elections that their contacts have participated in. Furthermore, there is evidence showing that an individuals decision-making is influenced by his contacts actions. The properties of voters within the social graph were also studied; results reveal that candidates who gain the support of an influential coalition tend to succeed in elections.
An Association Model Based on Modus Operandi Mining for Implicit Crime Link Construction
Jau-Hwang Wang and Chien-Lung Lin Link analysis has been an important tool in crime investigation. Explicit or implicit social links, such as kinship, financial exchange, telephone connection, links derived from modus operandi, time of day, and geographic relationship, are often used to construct links between criminals. This paper proposes an association model based on modus operandi mining to establish links among crime cases and chronic criminals. Two data sets of robbery and residential burglary crime records were collected from a local police department and were used for experiment to evaluate the performance of the proposed approach.
Countries Co-citation Network and Research Fronts of International Energy Technology

Jianhua Hou and Han Chen In this article, we draw countries cooperation networks joint with their research fronts of international energy technology. We derived the countries co-citation networks by first using graph-theoretical approaches as implemented in CiteSpace. We retrieved the documents by
77
topic word energy technolog* between 2001 and 2010 which is published by article type in English from web of science which contains SCI and SSCI database index. Based the cluster information, we analysis the distribution and the research fronts of international energy technology. Title Authors Abstract
Minimizing Interference through Channel Assignment in Multiradio Wireless Mesh Networks

Y. Kiran Babu, T. Narendra Babu, and B. Ramesh Breadth First Search Channel Assignment(BFSCA) is a hybrid channel assignment algorithm that utilize multiple radio interfaces to improve the throughput and minimize the interference within the wireless mesh network and between the mesh network and co-located wireless mesh networks. This new channel assignment scheme allows different nodes in the same network to communicate with each other without causing too much interference to their neighbors. It is introducing Multiradio Conflict Graph(MCG) to model interference in the wireless mesh network. Breadth First Search Channel Assignment considers both the fixed channels (static) and the dynamic channels to reduce interference of the network. BFSCA will increase the network throughput greatly.
Predicting Customer Demographics in a Mobile Social Network

S. Aarthi, S. Bharanidharan, M. Saravanan, and V. Anand A network made of individuals connected based on their communication behaviour using mobile phones can be called as a Mobile Social Network. Mapping and measuring of interactions and flows between people across mobile social networks are being performed extensively in an attempt to understand the intriguing patterns of human behaviour. Such analyses can help in arriving at useful inferences for improving the accuracy of Targeted Advertisements. This paper makes one such attempt to extract the demographics (i.e gender and economic status) of a person based on his/her connectivity in his/her respective social network(s) and mobile phone usage over a period of time. The need for prediction arises from the fact that, for prepaid users, the demographics are either unavailable or inaccurate. The results produced are evaluated and standardized based on proven statistics pertaining to the nation considered. We use candlestick charts to compare the experimental results.
Dense Subgroup Identifying in Social Network

Ye Conghuan The densest coherent subgraphs can provide valuable knowledge about the underlying internal structure of a social network, and mining frequently occurring coherent subgraphs of a large network has been witnessed several applications and received considerable attention in the graph mining community recently. However, some key players are not always appeared in the clique, therefore, clique detection could not identify some core members in social networks. In this paper, we define a
78
generalization of the dense subgraph problem by an additional distance restriction to the nodes of the dense subgraph which is a quasi-clique in fact. We propose a new quasi-clique detection algorithm based on the definition of dense subgraph, and a novel optimization techniques based on idea of synchronization, which can prune the unpromising and redundant alien from the dense subgraph. The proposed methods could discover quasi-cliques and core players that are not shown in clique. Title Authors Abstract
Effects of Mentoring on Player Performance in Massively Multiplayer Online Role-Playing Games (MMORPGs)
Kyong Jin Shim, Kuo-Wei Hsu, and Jaideep Srivastava Massively Multiplayer Online Role-Playing Games (MMORPGs) have become increasingly popular and have communities comprising millions of subscribers. With their increasing popularity, researchers are realizing that video games can be a means to fully observe an entire isolated universe. In this study, we examine and report our findings on the effects of mentoring activities on player performance in EverQuest II, a popular MMORPG developed by Sony Online Entertainment.
Title
Towards Named Entity Recognition Method for Microtexts in Online Social Networks: a Case Study of Twitter
Jason Jung Given a certain question, named entity recognition (NER) methods can be an efficient strategy to extract relevant answers. The goal of this work is to extend NER methods for analyzing a set of microtexts, which are short text on online social media. To do so, we propose two contextual closure properties to discover contextual clusters of microtexts, which can be expected to improve the performance of NER tasks. Experimental results demonstrate the feasibility of the proposed method for extracting relevant information in online social network applications.
Authors Abstract
Building Artificial Identities in Social Network Using Semantic Information

Kai Chen, Yi Zhou, Li Song, and Xiaokang Yang As the popularity of social networking sites increase, so does their attractiveness for criminals. In this work, we show how an adversary can build artificial identities using semantic information in social network. Our method make the identities look more like real people, therefore can be used to support many kinds of attacks, such as ASE [1], profile cloning [2]. A prototype of this method is implemented, includes following stages: Firstly, categories of virtual identity are predefined, and each category has multiple properties, such as geographical region, hobby, education, age, interested topic/keywords, etc. Secondly, based on category information, each identity will foster its own life semantically, such as edit profile and update status, find hot related news/topic from Google then post to wall, find related groups/networks then request to add in, and find/like/create/comment pages/posts, etc. Thirdly, artificial identity will evolve to multiple stages according to its status (for example,
79
number of friends of real people), single identity with different evolutionary stages is linked together to a group that will help to ensure the number of attack edges [3]. Title
A Novel Approach for Developing Automatic Knowledge Construction and Diagnostic System for Tag-Based Learning Environment
Jun Ming Chen, Ying Ying Chen, Yeali S. Sun, and Meng Chang Chen With the advent of Web 2.0 technology, researchers have attempted to use Web 2.0 tools to develop adaptive and cooperative learning environments. However, in building learning and teaching diagnostic system, one of the major difficulties is the lack of prior knowledge to help learners read and understand what they read in articles. Moreover, because of the lack of a mechanism to assist teachers in monitoring the running activities and student progress, such that constructive suggestions can be given to the students and tutoring strategies can be improved accordingly. Therefore, this paper presents a framework for calculating semantically meaningful prior knowledge and generating spreading energy for discovering students reading status in semantic networks using a modified version of Semantic Analysis and Social Network techniques. An application to the development of a Tag-based Collaborative reading learning system is very useful for teachers and students.
Authors Abstract
Title
A Social Network Approach to Examine the Role of Influential Stocks in Shaping Interdependence Structure in Global Stock Markets
Ram B Roy and Uttam Sarkar This paper investigates the role of influential stocks in shaping the emergent system-level interdependence in global stock markets using a large set of stocks selected from major stock market indices from across the globe. We have proposed a method to identify influential stocks using various centrality measures used in social network analysis literature. Our study shows how these influential stocks provide key linkages in integrating the global stock markets as an interconnected system. We have also shown that the regional influence dominates over the economic sector influence in shaping the topological structure of stock market network. The study also captures the change in the topology of this network following the collapse of Lehman Brothers.
Authors Abstract
Automatic Reputation Computation through Document Analysis : A Social Network Approach

JooYoung Lee, Yue Duan, Jae C. Oh, Wenliang Du, Howard Blair, Lusha Wang, and Xing Jin We develop and study two social network-based algorithms for automatically computing authors reputations from a collection of textual documents. First, given a set of documents, both algorithms examine keyword reference behaviors of the authors to construct a social network.
80
This social network represents the relationship among the authors in terms of information reference behavior. With the resulting network, the first algorithm computes each authors reputation value considering only direct referential activities while the second considers indirect activities as well. We discuss the reputation values computed by the two algorithms and compare them with the reputation ratings given by a human domain expert. We also analyze the social network through a community detection algorithm. We observed several interesting phenomena including the network being scale-free and having negative assortativity. Title
Private Information Transmission on the Consumer Generated Media: Information Privacy in the Japanese Context
Yohko Orito, Hitoshi Okada, and Hidenobu Sai This study examined private information transmissions on CGM/UGM websites from the perspective of the Japanese sense of information privacy. The characteristics of Japanese private information transmission on the CGM are described and discussed.
Authors Abstract
81
Conference Venue
ASONAM 2011
Brief Introduction to NUK
ASONAM 2011 will be held in National University of Kaohsiung (College of Management Building), Kaohsiung City, Taiwan. National University of Kaohsiung was founded in February 2000 under government auspices to achieve the balanced development of higher education between southern and northern Taiwan, and to help establish Taiwan as an Asia-Pacific Regional Operations Center. It is one of the leading academic institutions aiming for quality research and teaching in southern Taiwan. Currently the University has 5 colleges with a total of 19 departments, 27 master programs, and 3 doctoral programs, as well as 4 EMBA and 1 IMBA programs. For now, there is an enrollment of over 5,400 students and over 210 faculties.
NUK Campus Map
Conference Site
Building of College of Management, NUK
82

July 25, 2011.
Conference Reception
Conference welcome reception will take place in Garden Villa Kaohsiung on 18:30-21:00,
Conference Banquet
Conference Banquet will be held in The Splendor Kaohsiung on 19:00-21:30, July 26, 2011. The banquet site is located in the highest building (The 85 Sky Tower) of Kaohsiung city with amazing view to the Kaohsiung Harbor.
Internet Service
Room 108 in the Building of College of Management is designated for Internet access room containing seats with power and Ethernet sockets. Free Wi-Fi service is also available around the conference site (Building of College of Management) and most of the campus area. Please use the username/password provided in your conference bag for accessing the Wi-Fi service.
83
Conference Room Plan

ASONAM 2011
College of Management 1F/BF
84
College of Management 4F
85
Social Network Analysis and Mining

Published by Springer
Editors-in-Chief: Reda Alhajj University of Calgary, CANADA Nasrullah Memon University of Southern Denmark, DENMARK Volume 1 / Number 1 / January 2011: Volume 1 / Number 2 / April 2011: Volume 1 / Number 3 / July 2011: Dear Colleague, You are invited to consider Social Networks Analysis and Mining Journal, (SNAM) as the main outlet for your high quality research papers. The SNAM journal provides a rapid forum for the dissemination of original research articles in all areas of social networks analysis and mining as interdisciplinary research platform. Manuscripts should be submitted to the journal online at
http://www.springer.com/computer/database+management+%26+information+retrieval/journal/13278
http://www.springerlink.com/content/1869-5450/1/1/ http://www.springerlink.com/content/1869-5450/1/2/ http://www.springerlink.com/content/1869-5450/1/3/
The rapid increase in the interest in social networks has motivated the need for a more specialized venue with wider spectrum capable of meeting the needs and expectations of a variety of researchers and readers. Social Network Analysis and Mining (SNAM) is a multidisciplinary journal to serve both academia and industry as a main venue for a wide range of researchers and readers from social sciences, mathematical sciences, medical and biological sciences and computer science. The SNAM journal is proud to have an outstanding group of editors who widely and rigorously cover the multidisciplinary score of the journal. They are known to be research leaders in the field of social networks analysis and mining. Further, the SNAM journal is characterized by providing thorough constructive reviews by experts in the field and by the reduced turn-around time which allows research results to be disseminated and shared on timely basis. The target of the editors is to complete the first round of the refereeing process within about 8 to 10 weeks of submission. Accepted papers go to the online first list and are immediately made available for access by the research community. We look forward to receiving your submissions.
86
ASONAM
Call for Papers
ASONAM: The 2012 International Conference on Advances in Social Networks Analysis and Mining
August 2629, 2012 http:// asonam2012.etu.edu.tr Istanbul, Turkey
Honorary Chairs
Erol Arkun Bilkent University Jiawei Han University of Illinois at Urbana-Champaign
The study of social networks originated in social and business communities. In recent years, social network research has advanced significantly; the development of sophisticated techniques for Social Network Analysis and Mining (SNAM) has been highly influenced by the online social Web sites, email logs, phone logs and instant messaging systems, which are widely analyzed using graph theory and machine learning techniques. People perceive the Web increasingly as a social medium that fosters interaction among people, sharing of experiences and knowledge, group activities, community formation and evolution. This has led to a rising prominence of SNAM in academia, politics, homeland security and business. This follows the pattern of known entities of our society that have evolved into networks in which actors are increasingly dependent on their structural embedding. The international conference on Advances in Social Network Analysis and Mining (ASONAM 2012) will primarily provide an interdisciplinary venue that will bring together practitioners and researchers from a variety of SNAM fields to promote collaborations and exchange of ideas and practices. ASONAM 2012 is intended to address important aspects with a specific focus on the emerging trends and industry needs associated with social networking analysis and mining. The conference solicits experimental and theoretical works on social network analysis and mining along with their application to real life situations. General areas of interest to ASONAM 2012 include information science and mathematics, communication studies, business and organizational studies, sociology, psychology, anthropology, applied linguistics, biology and medicine. More specialized topics within ASONAM include, but are not limited to:
Anomaly detection in social network evolution Application of social network analysis Application of social network mining Communities discovery and analysis in large scale online social networks Communities discovery and analysis in large scale offline social networks Connection between biological similarities and social network formulation Contextual social network analysis Contextual social network mining Crime data mining and network analysis Cyber anthropology Dark Web Data protection inside communities Detection of communities by document analysis Dynamics and evolution patterns of social networks Economical impact of social network discovery Evolution of patterns in the Web Evolution of communities in the Web Evolution of communities in organizations Geography of social networks Impact of social networks on recommendations systems Information acquisition and establishment of social relations Influence of cultural aspects on the formation of communities Knowledge networks Large-scale graph algorithms for social network analysis Misbehavior detection in communities Migration between communities Multi-agent based social network modeling and analysis Open source intelligence Pattern presentation for end-users and experts Personalization for search and for social interaction Preparing data for Web mining Political impact of social network discovery Privacy, security and civil liberty issues Recommendations for product purchase, information acquisition and establishment of social relations Recommendation networks Scalability of social networks Scalability of Search algorithms on social networks Social and cultural anthropology Social geography Social psychology of information diffusion Temporal analysis on social networks topologies Visual representation of dynamic social networks Web mining algorithms Web communities
General Co-Chairs
Fazli Can Bilkent University Kathleen Carley Carnegie Mellon University Irwin King The Chinese University of Hong Kong Philip S. Yu University of Illinois at Chicago
Program Co-Chairs
Fakhri Karray University of Warerloo Faruk Polat Middle East Technical University
Industry Track Co-Chair

Charu Aggarwal IBM T.J. Watson Research Center
Sponsorship Co-Chairs
Hanghang Tong IBM T.J. Watson Research Center
Tutorials Co-Chairs
Ralf Klamma RWTH Aachen University Huan Liu Arizona State University Jie Tang Tsinghua University
Workshop Co-Chairs
VS Subrahmanian University of Maryland I-Hsien Ting National University of Kaohsiung
Panels, Exhibits and Demos Co-Chair

Hasan Davulcu Arizona State University Katina Michael University of Wollongong
Publicity Co-Chairs
Mehmet Kaya Firat University Keivan Kianmehr University of Western Ontario Ee-Peng Lim Singapore Management University Mohamad Nagi University of Bradford
Instructions for Authors Papers reporting original and unpublished research results pertaining to the above topics are solicited (Proceeding indexed by EI). Full paper submission deadline is March 15, 2012. These papers will follow an academic review process. Full paper manuscripts must be in English with a maximum length of 8 pages (using the IEEE two-column template). Submissions should include the title, author(s), affiliation(s), e-mail address(es), tel/fax numbers, abstract, and postal address(es) on the first page. Papers should be submitted to the conference Web site: asonam2012.etu.edu.tr. If Web submission is not possible, manuscripts should be sent as an attachment via email to [email protected] by March 15, 2012. The attachment must be in PDF or Word .doc format. Papers will be selected based on their originality, timeliness, significance, relevance, and clarity of presentation. Authors should certify that their papers represent substantially new previously unpublished work. Paper submission implies that the intent is for one of the authors to present the paper if accepted and that at least one of the authors must register for a full conference fee and attend the conference to present the paper.
Publications Co-Chairs
Panagiotis Karampelas Hellenic American University Jon Rokne University of Calgary
Local Arrangements Co-Chairs

Ahmet Bulut stanbul ehir University Tansel zyer TOBB Economics and Technology University
Registration Co-Chairs
Tansel zyer Mehmet Tan
Web Chair
Mehmet Tan TOBB Economics and Technology University
87
Oct 2011 Nov Dec Jan Feb 2012 Mar Apr May Jun Jul
88
89

As On Am Program

Uploaded by

Copyright:

Available Formats

As On Am Program

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

As On Am Program

Uploaded by

Copyright:

Available Formats

ASONAM 2011

Kaohsiung City Government

Bureau of Foreign Trade

IEEE Computer Society

IEEE Systems, Man, Cybernetics Society

Honorary General Chairs

Local Arrangement Chairs

Workshop / Special Session Chairs

Hsin-Chang Yang, National University of Kaohsiung

A Message from the General Chairs

A Message from the Program Chairs

Reda Alhajj, Nasrullah Memon, and I-Hsien Ting Program Chairs

Conference Program At a Glance

Day 1: July 25 (Monday)

Day 2: July 26 (Tuesday)

Day 3: July 27 (Wednesday)

Statistical Models for the Analysis of Social Networks

Monday, July 25, 2011 Prof. Reda Alhajj

Social Network Mining for People Search

Monday, July 25, 2011 Prof. Tansel zyer

Tuesday, July 26, 2011 Prof. Nasrullah Memon

Towards Integrated Mining of Multiple Social and Information Networks

Tuesday, July 26, 2011 Prof. Vincent S. Tseng

Wednesday, July 27, 2011 Prof. Von-Wun Soo

Information Processing in Social Networks

Wednesday, July 27, 2011 Prof. Ambuj K. Singh

Featured Events Meals and Social Events Day 1: July 25 (Monday)

Day 2: July 26 (Tuesday)

Day 3: July 27 (Wednesday)

Contextual Social Network Analysis (I)

The ML-model for Multi-Layer Social Networks

Title Authors Abstract

Tag-based User Topic Discovery using Twitter Lists

Title Authors Abstract

Content-based Modeling and Prediction of Information Dissemination

SCENE: Structural Conversation Evolution NEtwork

Scalability in Social Network Analysis

DisNet: A Framework for Distributed Graph Computation

Title Authors Abstract

Title Authors Abstract

Probabilistic Subgraph Matching on Huge Social Networks

Shortest Path Discovery in the Multi-layered Social Network

Title Authors Abstract

Discovering Explorative Patterns from Real World Complex Networks

(Workshop) The First International Workshop on Mobile Social Network

10:50-12:30 Chair: Title Authors

July 25 (Monday) Dr. Kun-Lung Wu

GPS Data Based Urban Guidance

Title Authors Abstract

A Framework of Recommendation System Based on both Network Structure and Messages

Title Authors Abstract

Bayesian Filters for Mobile Recommender Systems

Assessing Media Relevance via Eye Tracking

Title Authors Abstract

Information Acquisition and Establishment of Social Networks

10:50-12:30 Chair: Title Authors Abstract

July 25 (Monday) Prof. Chien-Hsing Wu

Extracting Social Networks to Understand Interaction

Entity Resolution using Social Graphs for Business Applications