IOP Conference Series: Materials Science and Engineering

PAPER • OPEN ACCESS You may also like

- Big data analytics as a service
Big Data Analytics Applicability in Higher Learning infrastructure: challenges, desired
properties and solutions
Educational System Manuel Martín-Márquez

- Research Review on Big Data Usage for

Learning Analytics and Educational Data
To cite this article: R. Tasmin et al 2020 IOP Conf. Ser.: Mater. Sci. Eng. 917 012064 Mining: A Way Forward to Develop an
Intelligent Automation System
A Yunita, H B Santoso and Z A Hasibuan

- Opportunity and Challenges for Migrating

Big Data Analytics in Cloud
View the article online for updates and enhancements. S Amitkumar Manekar and G. Pradeepini

This content was downloaded from IP address 122.183.51.128 on 03/02/2023 at 04:04

International Conference on Technology, Engineering and Sciences (ICTES) 2020 IOP Publishing
IOP Conf. Series: Materials Science and Engineering 917 (2020) 012064 doi:10.1088/1757-899X/917/1/012064

Big Data Analytics Applicability in Higher Learning

Educational System

Tasmin, R. 1, Muhammad, R. N 1,2 and A. H. Nor Aziati 1

1
Department of Technology Management, Universiti Tun Hussein Onn Malaysia, 86400, Parit
Raja, Johor.
2
Midland School of Business and Finance, Abuja, Nigeria.
Corresponding author: [email protected]

Abstract. The application of big data analytics is significantly gaining awareness in the
educational sector as universities are operating under pressure in an increasingly competitive
environment. Quite a number of researchers have reported the use and application of big data
in different fields with few publications addressing the integrative application of big data
analytics in institutions of higher education. The purpose of this paper is to explore the
applicability of big data analytics in higher institutions. This paper outlines the major areas in
which big data analytics can be of use in the higher institutions such as in academic and
management levels. The ultimate goal is to optimize using big data analytics in learning and
decision-making.

1. Introduction
Over the years with the advancement in areas of information technology, artificial intelligence, and
machine learning, the amount of information been processed is continually increasing at an
unprecedented rate [1]. Due to this huge deposit of information and the difficulty in processing, the
technique of big data was developed. The technique involves the process of analyzing large data in a
timely, simplified, and efficient manner [2]. Today, the use of big data technique has been gaining
attention in several application domains. IT companies, small and large scale business enterprise,
health care systems, sports, securities, among others, have been adapting the concept and techniques of
big data in enhancing their activities. For this purpose, data science has become one of the most sort
profession globally [3]. Big data analytics is defined as the processing of vast amount of data using
mathematics and statistical modeling, programming and computing algorithm techniques for finding
actionable value [4]. Big data applications are meant to gain insights, discover patterns, and identify
abnormalities across numerous dataset within an organization [5]. Most importantly, big data analytics
use in organizations will improve decision making for managers, and provide better customer services
in business, optimize resources, and better understanding of customer engagement patterns [6].

Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution
of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
Published under licence by IOP Publishing Ltd 1
International Conference on Technology, Engineering and Sciences (ICTES) 2020 IOP Publishing
IOP Conf. Series: Materials Science and Engineering 917 (2020) 012064 doi:10.1088/1757-899X/917/1/012064

Many types of research have been carried out with big data in several fields such as business
companies tracing their contents on several social media networks to perform analysis, public-sector
organizations, healthcare systems monitoring various networks and research to evaluate and treat
various epidemics [7]. Some of the reports on big data use in various areas include the availability of
data, its relevance, benefit, opportunities, cost, and ownership and also, its applicability [8]. However,
there are few reports and publications on the use of big data in the higher education system (HEIs) [9].
Decision-making is a fundamental feature in every organisation, which can be viewed based on
organisation’s perception. Generally, data-driven decision-making is the primary measure considered
as a good management by organisation. In higher education sector, every institution has their unique
way towards decision-making approach aiming at upholding its operations. Typically, it is the
responsibility of the executives of higher education to make decision, which is usually based on the
executives’ intuition and experience [10]. [11] carried out a survey on 380 senior managers in IT
departments with the objective of understanding the use of data and how it improves the processes of
decision-making. The result shows that data-based decision-making in higher education is a significant
basis of sustainable competitive advantage.
Similarly, [11] conducted multiple research, in which the first study investigated how
administrators of faculty at a higher institution in California used student data in decision-making. The
second study was the use and influence of data at large at the institution. Both studies indicated that
although institutions have data management approach, however, they are yet to attain its full gain.
Therefore, with the potential of big data technologies, organizational tasks, importantly in the HEIs
can optimize some of the challenges especially in the area of strategic management and policy. HEIs is
a good application area for big data analytics as there are untapped potentials where the technique
could be applicable. The universities have large amount of data such as registration data, alumni data,
course outline data, students’ data, assessment data, tutor data, among others. Applying big data in
mining could help provide easy access and processing which will then help to enhance the workflow
in the educational system. The analytics of big data in HEIs is broadly categorized [12] into two:
academic and learning.
Academic analytics is broadly referring to as data-driven decision-making practices of analysing
institutional data (large data sets, statistical techniques, and predictive modeling) to generate
actionable intelligence for operational purposes in an education institution [12]. It has the potential of
cost-benefit to the institution, the increment in the student recruitment and a better quality of education
which will provide a competitive advantage for institutions. On the other hand, learning analytics is
the analysis of a large data sets of student’s data which is generated and collected to measure academic
progress, predict future performance, and site possible difficulties [13]. It has significant positive
influence on tutoring, curriculum, assessment, and decisions which are usually made at the classroom,
university, or policy level by academicians, administrators, and policymakers. With the emergence of
big data and its applications, collection and storage of data are held in incredible magnitudes. The
application of big data has had massive positive impact on solving real-world scenarios. [14] presented
in their findings that Facebook in about two years has around 500 million users. On the social media,
information is being processed almost every seconds. [15] pointed out that within a short time,
companies globally will have stored data exceeding seven exabytes.
Despite the benefits of big data, there are some challenges concerning its usage and application.
[16] highlighted in his study some significant preliminary obstacles of big data which includes;
workers who are from technological or business fields but do not have adequate skills of big data,
inadequate infrastructure, and handling of categories of data from diverse sources (unstructured and
semi-structured data). Others include an indecisive choice of technique and methodologies to analyze
data to be able to overcome these obstacles and the problem of agreeing and understanding between an
organization and a third party (the hiring of expert outside an organization to manage big data). Also,
the problem within a collaboration between stakeholders, security and privacy among others. In this
paper, the applicability and impact of big data analytics in institution of higher education is explored.
Therefore, the objective of this paper is to fill the gap of big data uses in universities by exploring the
applicability of Big Data analytics in institutions of higher education. The remainder of this paper is
organized as follows. Section 2 presents the works related to Quranic text classification, Section 3

2
International Conference on Technology, Engineering and Sciences (ICTES) 2020 IOP Publishing
IOP Conf. Series: Materials Science and Engineering 917 (2020) 012064 doi:10.1088/1757-899X/917/1/012064

presents the methodology with detailed account of the dataset, classification experiment as well as the
evaluation metrics, Section 4 reports the experiment results, and finally Section 5 concludes with some
directions for future work.

2. Big Data
Big data is based on the concept that voluminous data can be processed, analyzed and treated using big
data analytics. There is no specific definition of big data yet, as many experts define big data as its
suite their purpose. [17] stated that big data is an asset of Information (data) considered by its high
volume, variety, and velocity which require specific technology and analytical approaches for its
revolution into value. Likewise, [2] reviewed that big data refer to the concept that the volume of data
requires much more robust technologies, techniques and people with new skills to treat, process and
analyze large dataset in a simplified, timely way. Therefore, the technology of big data can help
organizations to sustain and gain competitive advantage internationally. Big data analytics is
correlated with business intelligence and is supported in statistical analysis and data mining [17]. It is
on the basis of data-driven decision making [18].
Recently, more than 75% of companies exceptionally private organizations have already started
implementing the concept of big data in order to optimize their strategies and support improvement of
new products and services [19]. Big data analytics enable organizations to manage large amount of
data within a short time. This helps to gain competitive advantage by allowing management to have
better handling of data processing [20]. Big data analytics have the potential to advance the
performance, provides decision making support to facilitate innovation in the products and services of
business standards [21]. Furthermore, the concept involves data discovery, visualization, and advanced
analytics [3]. There are several standard techniques organizations use for big data analytics such as:
MapReduce, Scalable Hadoop, Spark, YARN (for batch processing engine), Apache Kafka, Apache
Samsa, and Apache Storm (for distributed stream processing engine) [22].

3. Application of Big Data Analytics in Higher Education Sector

Big data Application of Big Data in HEIs is still in its early stage. The universities have a large
amount of data that could be mined using big data applications. The pressure on HEIs concerning
graduating students is a global challenge [23]. However, with the techniques of big data, the analytics
of large data has the potential of creating actionable value that could improve the success of students,
improve the quality of teaching, and also ease the learning process for students. In addition, the
application of big data analytics to HEIs also help promote awareness for parents, tax payers, and
stakeholders, whom are integral components of an educational system [12], [8].
Big data can be mapped to higher institutional data as it can be applied to learner, tutors,
department, and faculty depending on the aim and purpose in which it needs to be analyzed. Analytics
in higher education system have various descriptions parallel to where the analytics are purposeful
[13]. Big data analytics techniques can be used to analyze, manipulate, store and find meaningful
information for decision making in higher institutions. The use of big data in HEIs as shown in Figure
1 and further illustrated in Table 1 is mainly categorized as academic and learning analytics [20].

3
International Conference on Technology, Engineering and Sciences (ICTES) 2020 IOP Publishing
IOP Conf. Series: Materials Science and Engineering 917 (2020) 012064 doi:10.1088/1757-899X/917/1/012064

Figure. 1: Schema Big data mapping in HEIs.

A. Academic Analytics
Big data analytics in academics has to do with the development of resources, improving processes and
workflows of the academic institution by use of the institutional, academic and student data. [24]
regards academic analytics as the combination of institutional data, arithmetical analysis, and
predictive modeling to create intelligence with which students, instructors, or administrators can
change the academic pattern of its institution. Big data analytics can be applied in academics as
follows:
 Students admission by use of predictive modeling to allow the offices of admission and
administrative units predict better and manage the size and admission pattern for new students
to be enrolled.
 Decision making for the administrative officers and the stakeholders using analytical models
and data mining approaches to find, understand and reoccurrences of patterns in data [12].
Also, to identify new trends of data in which significant value can be attained from the data
such that the right decision can be taken according to the situation for the betterment of the
institution.
 Alumni data can be analyzed by big data analytics to statistically forecast graduate
employability in society. Big data analytics can be applied for fundraising by using predictive
models to identify and examine the alumni information to predict those most likely to donate
[12]. Big data analytics can also help students to get to know about the skills that they need
that can be suitable for their dream jobs [25]. Therefore, making graduates get appropriate
jobs.
 Other areas where academic analytics of big data could be applied include resource allocation,
budget (finance), strategic planning, staff-centric services, Attrition patterns, industrial
collaborations and linkages, and transportation management.

B. Learning Analytics
Learning analytics focuses on the success of the students. This involves the use of predictive
analytics and processes to collect, analyze, use, integrate generated and actionable student data with
the purpose to improve the performance of students and teaching of teachers. Learning analytics can
also be used to substitute tables of data with dashboards that give an instant response about academic
goals, student needs, and targets [8]. Additionally, big data is also said to have replace human
decision-making by using automated algorithms [26]. The fundamental of learning analytics involves
capturing and analysis of data to improve learning for students. [12] stated that the analysis process of
learning analytics has five phases. The steps include (a) Capturing; data collected in real-time from
various sources such as course management systems (CMS), virtual learning environments (VLE),
personal learning environment, forums, web portals, chat rooms are combined with student data [27];
(b) Reporting; the collected data is used to generate precise patterns for recognizing and measuring the

4
International Conference on Technology, Engineering and Sciences (ICTES) 2020 IOP Publishing
IOP Conf. Series: Materials Science and Engineering 917 (2020) 012064 doi:10.1088/1757-899X/917/1/012064

student’s progress. Afterward, learning analytics dashboards use visualization for a better
understanding of the data [28]; (c) Predicting; the visualized data is used for predicting the
performance of student, success and also for identifying students at risk. Also, the predictive models
can be used for decision making and policies about courses and resource allocation and the decision-
makers of the institutions [29], [30]; (d) Acting; the information obtained from the processing and
analysis of data is use to set appropriate interventions especially with regard to students at risk of
failure or dropping out [31]; (e) Refining; the gathered data is used in a recurrent process for constant
developments of the operated model in teaching and learning for both tutors and students [32]. Big
data analytics can be applied to learning analytics as follows:
 Tracking student performance: Analytics of big data such as analytical dashboard can be applied
to mine data stored in its cloud-based platform using real-time analysis to predict which
students are struggling, under pressure and at risk of dropping out, understand and improve the
performance of the students.
 Retention rate can be potentially improved by applying big data analytics such as adaptive
learning analytics with the use of course management system data to build a predictive model
that will identify and examine the students who are academically struggling. This way, early
warning, and counseling can be proactively provided to such students.
 Scholarship can be awarded to students in need by using predictive analytics to create a model
utilizing the student profile to identify students who are have not paid their bills or are
struggling to pay.
 Student clubs and activities help the student to develop a healthy mental system. Students can
learn a lot from programs available such as academic tutoring and advising, fitness
educational programs, social activities and services (student organization memberships),
sessions advising, career for both staff and students in the institution. All these programs can
be created and managed with the application of big data analytics such as social network
analysis for using data from both manual and online records [33]. Other applicability of big
data analytics in learning analytics includes admission pattern, talent, and leadership.
The integrative platforms of big data analytics can use various machine language and statistical
analysis to identify difficulties, threats, and opportunities. Consequently, as shown in Figure 2,
education can become active, cheaper, operations can be provided, and learning strategies can be
enhanced [34], which is also presented in Table 1. Therefore, the quality of education can be
improved.

Figure. 2: Analytics in Higher Education Institutions.

5
International Conference on Technology, Engineering and Sciences (ICTES) 2020 IOP Publishing
IOP Conf. Series: Materials Science and Engineering 917 (2020) 012064 doi:10.1088/1757-899X/917/1/012064

Table 1. Summary of the Applicability of Big Data Analytics in Education.

Big Data Descriptions Applicability Level Beneficiaries

Analytics
Analytics Data evaluation and analysis that Can be applied to all Learner, Tutor,
enables the assessment, levels of the institution Department,
improvement of tutors, for better data-driven Institution
programs, departments, decision making.
institutions and as well as
predicting and comparing the
learner's performance.
Academic Decision making primarily on The Institutional Learner, Tutor,
Analytics the operation and financial of the students’ profiles, Faculty,
institution (academic students’ enrollment, Administrator, and
difficulties) by using the support academicians’ profiles, Stakeholder
of information technology. alumni and research
profiles

Learning It can also be referred to as the Students’ recruitment, Learner, Tutor, and
Analytics interpretation of an institutional course management, Department
data generated and collected performance, retention
regarding the learners to
measure academic progress,
predict future performance to
improve the decision making of
the institution.

4. Successful Case Examples of Analytics Application in universities

Some higher education institutions are progressively implementing analytics especially the
development of curriculum design for the student to create a centre of attention for intending students,
enhance both student retention and graduation rates and gain funding from the government [5]. For
examples, some of the institution already using predictive analytics in USA universities and colleges
to optimize central units of the institution, such as student behaviour and activities and to support their
funds with their institutional objectives. Arizona State University has implemented analytics using
College Scheduler as an analytics solution into their system using Civitas Learning as the service
provider [1] Similarly, Sinclair Community College, University of Oregon have also implemented
analytics using Visual Analytics solution and SAAS as the service provider [4].
Arizona State University implemented analytics to enhance academic experience students’, and
as a result of this, the graduation rate has increased by 20% [33]. The university is applied analytics
software known as College Scheduler. It is a software design which allows students to input individual
and confidential information into a dashboard. The platform considers students’ academic and
personal requirements and auto-fills the mandatory courses they must take [35]. The software is
beneficial as it prevents students from taking courses that are not relevant to their majors, hence helps
in managing their time and financial funds [36]. [37] ascertained that the College Scheduler software
could improve the rate of college completion by more than 3%. Another university that has applied
analytics is the University of Maryland – College Park. The college targeted management of students’
performance, by using analytics to predict student success or failure and forward advising and with the
implementation, the college has gained by supporting limited success gaps for low-income students,
shortened graduation time and thereby improved graduation rates [38].

6
International Conference on Technology, Engineering and Sciences (ICTES) 2020 IOP Publishing
IOP Conf. Series: Materials Science and Engineering 917 (2020) 012064 doi:10.1088/1757-899X/917/1/012064

5. Challenges of Big Data Analytics in Higher Education Sector

Big data analytics offers numerous benefits that are of great impacts in resolving critical issues of the
educational system. However, accompanied with the benefits are some challenges. Some of the critical
challenges of big dat management are analytical and technical challenges. Analytical challenges cover
the volume, storage, analysis and quality of the data. [39]state that available data in an organization
may be in multiple format such as structured, semi-structured or unstructured. With the continuous
increase of data, managing it would be a challenge. Similarly, [40] explained that working with
heterogeneous data is time consuming and very expensive. To add, there are also issues such as data
collection, management, storage, data protection, privacy, and data ownership-which may be caused
by the teachers and students to question who get access to information and security of the data [38].
Another major challenge of applying big data in aspect of learning analytics is that the analytics may
focus more intensely on the technological context particularly in collection and analysis of data, rather
than showing what data should be collected and analyzed and for what purpose such data could be
used [41].

6. Conclusion
With high demand on the education system to improve the quality of education, there is no doubt, that
application of big data analytics has the potential to impact, transform and produce a better outcome
especially regarding strategic planning and policy in the education system. This will enable the
education system to develop new ways of attaining excellence in both teaching and learning.
Therefore, enabling continual development on the activities of student data which can be aggregated
and collectively supported with other educational data to give a better descriptive of the effectiveness
and successively of learning and teaching at institutions. Big data analytics provides for students
meaningful which helps them towards achieving academic success. Also, adapting learning analytics
in institutions could help students improve performance, skills, and knowledge in a more personalized
and self-paced way. Big data analytics in education can be ascertained to provide a better
understanding of educators, of how effective their subjects are being understood and applied by
students. Hence, the application of big data analytics in higher education system provides
opportunities and supports for students, educators, faculty, deans, senior management, education
authorities and ultimately the government. However, identifying or choosing the right analytics to
apply, integration of those databases and the selection of appropriate data to be used to get the best
insight especially in decision-making are still significant challenges in the education industry.

Acknowledgement
The authors highly appreciate Universiti Tun Hussein Onn Malaysia (UTHM) for funding this
research work under the Fundamental Research Grant Scheme FRGS vot K20

References
[1] Adeleke A O, Samsudin N A, Mustapha A, Nawi N M 2018 A Group-Based Feature Selection
Approach to Improve Classification of Holy Quran Verses, International Conference on Soft
Computing and Data Mining 282-297
[2] Fisher D, DeLine R, Czerwinski M, Drucker S 2012 Interactions with big data
analytics, interactions 19(3) 50-59
[3] Davenport T H, Patil D J 2012 Data scientist, Harvard business review 90(5) 70-76
[4] Elgendy N, Elragal A 2014 Big data analytics: a literature review paper, Industrial Conference
on Data Mining 214-227
[5] Crawford K, Schultz J 2014 Big data and due process: Toward a framework to redress
predictive privacy harms, BCL Rev 55(93)
[6] Bates D W, Saria S, Ohno-Machado L, Shah A, Escobar G 2014 Big data in health care: using
analytics to identify and manage high-risk and high-cost patients, Health Affairs 33(7) 1123-
1131
[7] Chandarana P, Vijayalakshmi M 2014 Big data analytics frameworks, International
Conference on Circuits, Systems, Communication and Information Technology Applications

7
International Conference on Technology, Engineering and Sciences (ICTES) 2020 IOP Publishing
IOP Conf. Series: Materials Science and Engineering 917 (2020) 012064 doi:10.1088/1757-899X/917/1/012064

(CSCITA) 430-434
[8] Chaurasia S S, Rosin A F 2017 From Big Data to Big Impact: analytics for teaching and
learning in higher education, Industrial and Commercial Training
[9] Bienkowski M, Feng M 2012 Enhancing teaching and learning through educational data
mining and learning analytics: An issue, Proceedings of conference on advanced technology
for education 1-64
[10] Daniel B 2015 B ig D ata and analytics in higher education: Opportunities and
challenges, British journal of educational technology, 46(5) 904-920
[11] Molina H M 2019 Big-Data Readiness of Four-Year Public and Private North Carolina Higher
Education Institutions, ProQuest LLC
[12] Campbell J P, DeBlois P B, Oblinger D G 2007 Academic analytics: A new tool for a new
era, EDUCAUSE review 42(4) 40
[13] Van Barneveld A, Arnold K E, Campbell J P 2012 Analytics in higher education: Establishing
a common language, EDUCAUSE learning initiative 1(1) l-ll
[14] Bughin J, Chui M, Manyika J 2013 Ten IT-enabled business trends for the decade
ahead, McKinsey Quarterly
[15] Manyika J 2011 Big data: The next frontier for innovation, competition, and
productivity, http://www. mckinsey. com/Insights/MGI/Research/
[16] Russom P 2013 Managing big data, TDWI Best Practices Report, TDWI Research 1-40
[17] Adnan K, Akbar R, Wang K S 2019 Information Extraction from Multifaceted Unstructured
Big Data, International Journal of Recent Technology and Engineering (IJRTE) 8 1398-1404.
[18] Manohar A, Gupta P, Priyanka V, Uddin M F 2016 Utilizing big data analytics to improve
education, ASEE
[19] Gantz J, Reinsel D 2011 Extracting value from chaos, IDC iview 1142 1-12
[20] Patel M R, Desai T 2016 Big Data Analytics in Optimizing the Quality of Education:
Challenges, International Journal for Innovative Research in Science & Technology 3(6) 165-
167
[21] Khan N, Yaqoob I, Hashem I A T, Inayat Z, Ali M, Kamaleldin W, Gani A 2014 Big data:
survey, technologies, opportunities, and challenges, The scientific world journal 2014
[22] Halaweh M, Massry A E 2015 Conceptual model for successful implementation of big data in
organizations, Journal of International Technology and Information Management 24(2) 2
[23] Neubaum D O, Pagell M, Drexler Jr J A, Mckee-Ryan F M, Larson E 2009 Business education
and its relationship to student personal moral philosophies and attitudes toward profits: An
empirical response to critics, Academy of Management Learning & Education 8(1) 9-24
[24] Baepler P, Murdoch C J 2010 Academic analytics and data mining in higher
education, International Journal for the Scholarship of Teaching and Learning 4(2) 1-9
[25] Picciano A G 2012 The evolution of big data and learning analytics in American higher
education, Journal of asynchronous learning networks 16(3) 9-20
[26] Jagadish A C, Johannes Gehrke, Alexandros Labrinidis, Yannis Papakonstantinou, Jignesh M
2014 Big data and technical chanlleges, 57(7) 86-94
[27] Tseng S F, Tsao Y W, Yu L C, Chan C L, Lai K R 2016 Who will pass? Analyzing learner
behaviors in MOOCs, Research and Practice in Technology Enhanced Learning 11(1) 8
[28] Ruipérez-Valiente J A, Muñoz-Merino P J, Leony D, Kloos C D 2015 ALAS-KA: A learning
analytics extension for better understanding the learning process in the Khan Academy
platform, Computers in Human Behavior 47 139-148
[29] Ain N, Kaur K, Waheed M 2016 The influence of learning value on learning management
system use: An extension of UTAUT2, Information Development 32(5) 1306-1321
[30] Akhtar S, Warburton S, Xu W 2017 The use of an online learning and teaching system for
monitoring computer aided design student participation and predicting student
success, International Journal of Technology and Design Education 27(2) 251-270
[31] De Freitas S, Gibson D, Du Plessis C, Halloran P, Williams E, Ambrose M, Arnab S 2015
Foundations of dynamic learning analytics: Using university student data to increase
retention, British journal of educational technology 46(6) 1175-1188

8
International Conference on Technology, Engineering and Sciences (ICTES) 2020 IOP Publishing
IOP Conf. Series: Materials Science and Engineering 917 (2020) 012064 doi:10.1088/1757-899X/917/1/012064

[32] Nam S, Lonn S, Brown T, Davis C S, Koch D 2014 Customized course advising: investigating
engineering student success with incoming profiles and patterns of concurrent course
enrollment, Proceedings of the Fourth International Conference on Learning Analytics And
Knowledge 16-25
[33] Reid-Martinez K, Michael M 2015 Big data in education: Harnessing Data for Better
Education Outcome, 3 33
[34] Ward H, Brown R, Hyde-Dryden G. Assessing Parental Capacity to Change when Children
are on the Edge of Care: an overview of current research evidence. London, United Kingdom:
Department for Education 2014
[35] Siemens G, Long P 2011 Penetrating the fog: Analytics in learning and education, EDUCAUSE
review 46(5) 30
[36] Siemens G 2012 Learning analytics: envisioning a research discipline and a domain of practice,
Proceedings of the 2nd international conference on learning analytics and knowledge 4-8
[37] De Mauro A, Greco M, Grimaldi M 2016 A formal definition of Big Data based on its essential
features, Library Review 65(3) 122-135
[38] Meenakumari J, Kudari J M 2015 Learning Analytics and its challenges in Education Sector a
Survey, Int. J. Comput. Appl 0975-8887.
[39] Jagadish H V, Gehrke J, Labrinidis A, Papakonstantinou Y, Patel J M, Ramakrishnan R,
Shahabi C 2014 Big data and its technical challenges, Communications of the ACM 57(7) 86-
94
[40] Labrinidis A, Jagadish H V 2012 Challenges and opportunities with big data, Proceedings of
VLDB Endowment 5(12) 2032-2033
[41] Sclater N, Peasgood A, Mullan J 2016 Learning analytics in higher education, London:
Jisc. 8(2017) 176