Scribd
Upload
2K views

Applications of Community Mining Algorithms

The document discusses several software tools for network analysis including JUNG, Netminer, Pajek, and igraph. It also discusses techniques for network reduction, discovering collaboration groups from social networks, and mining communities from distributed and dynamic networks. Key applications involve finding collaboration patterns among researchers and discovering communities in distributed networks using an autonomy-oriented computing approach.

Uploaded by

Nelson Raja
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
2K views

Applications of Community Mining Algorithms

The document discusses several software tools for network analysis including JUNG, Netminer, Pajek, and igraph. It also discusses techniques for network reduction, discovering collaboration groups from social networks, and mining communities from distributed and dynamic networks. Key applications involve finding collaboration patterns among researchers and discovering communities in distributed networks using an autonomy-oriented computing approach.

Uploaded by

Nelson Raja
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 17

 JUNG

(http://jung.sourceforge.net/)
 Netminer
(http://www.netminer.com/NetMiner/overview 01.jsp)
 Pajek
(http://vlado.fmf.unilj.si/pub/networks/pajek/)
 igraph
(http://igraph.sourceforge.net/)
 SONIVIS
(http://www.sonivis.org/)
 Commetrix
(http://www.commetrix.de/)
 NetworkWorkbench
(http://nwb.slis.indiana.edu/)
 visone
(http://visone.info/)
 CFinder
(http://www.cfinder.org/)
Borko Furht, “Handbook of Social Network Technologies and Applications”,
Springer, 1st edition, 2010.
 Network Reduction
 Discovering Scientific Collaboration Groups
from Social Networks
 Mining Communities from Distributed and
Dynamic Networks
 Network reduction is an important step in
analyzing social networks.
 Example
 The bibliography contains 360 papers written by
314 authors.
 community structure is detected using a
community mining algorithm, called ICS
 Most of the detected communities are self-
connected components.
 the clustered coauthor network can be reduced
into a much smaller one by condensing each
community as one node
 the top-level condensed network corresponding
to a 3-community structure is constructed by
using ICS from the condensed network
 In this way, a dendrogram corresponding to the
original coauthor network can be built

 The dendrogram of the coauthor network


IFETCE\M.E CSE\III SEM\NE7012-SNA\UNIT 3-PPT 10
 Flink is a social network that describes the
scientific collaborations among 681 semantic
Web researchers
 From the perspective of social network analysis,
one may be especially interested in such
questions as:
1. among all researchers, which ones would more
likely to collaborate with each other?
2. what are the main reasons that bind them together?
 Apply the community mining techniques.
IFETCE\M.E CSE\III SEM\NE7012-SNA\UNIT 3-PPT 13
 The self-organized communities would provide the
answer to the first question.
 By referring to them, one can know the specific
collaboration activities among these researchers.
 After manually checking the profiles of members
within different communities, an interesting fact has
been confirmed.
 most of communities are organized according to the
locations or the research interests of their respective
members.
 Answers the second question, i.e., researchers in
adjacent locations and with common interests prefer
to intensively collaborate with each other.
 Applications involve distributed and
dynamically-evolving networks
 Resources and controls are not only decentralized
but also updated frequently.
 We need find a way to solve a more
challenging NCMP
 to adaptively mine hidden communities from
distributed and dynamic networks.
 Solution is based on an Autonomy-Oriented
Computing (AOC) approach
 In AOC approach, a group of self-organizing
agents are utilized.
 The agents will rely only on their locally acquired
information about networks.
 Example: In Intelligent Portable Digital
Assistants
 selecting individuals who have frequently contacted
or been contacted with the user during a certain
period of time
 taking the selected individuals as the input to an AOC-
based algorithm
 ranking and recommending new persons
IFETCE\M.E CSE\III SEM\NE7012-SNA\UNIT 3-PPT 17

You might also like