2020 / 11(2)

Big Data Analytics in Higher Education: A Systematic Review *

Yükseköğretim’de büyük veri analitiği: sistematik bir literatür taraması

Zeynep AYTAÇ 1, [email protected]

Hasan Şakir BİLGE 2, [email protected]

Received: 07.02.2020; Accepted: 16.09.2020

The learning techniques and environment in education has Eğitimde öğrenme teknikleri ve ortamları son bir kaç yıl
been changing and developing in the last few years. The data içerisinde farklılaşmakta ve gelişmektedir. Çevrimiçi
obtained from the activities in online learning environments öğrenme ortamlarındaki etkinliklerden elde edilen veriler,
constitute an important data source for improvement and büyük veri teknolojileri kullanılarak yükseköğrenimdeki
development studies in higher education using big data iyileştirme ve geliştirme çalışmaları için önemli veri
technologies. This study is based on a review of the literature kaynakları oluşturmaktadır. Bu çalışma gelişmekte olan
that focused on the evolving area of big data analytics in büyük veri analitiği alanının, yükseköğrenimde literatürün
higher education. Four groups of stakeholders, namely gözden geçirilmesine dayanmaktadır. Bu çalışmada,
students, educators, administrators and course developers, yükseköğretimde öğrenciler, eğitimciler, yöneticiler ve ders
in higher education are discussed in this study by utilizing geliştiriciler olmak üzere dört paydaş grubu, büyük veri ve
big data and the conceptual model of educational big data eğitimsel büyük veri analitiğinin kavramsal modeli
analytics. We also discussed different learning kullanılarak tartışılmıştır. Ayrıca bu araştırmada farklı
environments in a framework in this research. The main öğrenme ortamları da bir yapı içerisinde tartışılmıştır. Bu
objective of this study is to systematically review 40 çalışmanın temel amacı, yüksek öğrenimde büyük veri
published articles on big data analytics in higher education analitiğinin hangi konulara daha çok yöneldiğini belirlemek
in order to determine the subjects of big data analytics in için yüksek öğrenimde büyük veri analitiği ile ilgili
higher education. Based on the findings of the literature yayınlanmış 40 makaleyi sistematik olarak incelemektir.
review, especially the curriculum development studies were Literatür taramasından elde edilen bulgulara dayanılarak,
examined and critical findings were discussed. özellikle müfredat geliştirme çalışmaları incelenmiş ve kritik
bulgular tartışılmıştır.

Keywords: Big Data, Higher Education, Learning Anahtar Kelimeler: Büyük Veri, Yükseköğretim,
Environments, Curriculum Development Öğrenme Ortamları, Müfredat Geliştirme

* 29 Mart 2019’da International Instructional Technologies in Engineering Education Conference (IITEEC)’da bildiri
olarak sunulmuştur.
1 Aksaray Üniversitesi, İktisadi İdari Bilimler Fakültesi

2 Gazi Üniversitesi, Mühendislik Fakültesi

Aytaç, Z., & Bilge, H. Ş.
IUYD’2020 / 11(2)

1. INTRODUCTION
Many institutions are operating in a competitive environment because of great number of
students and diverse student profiles, national and global economic, social and political
changes (Daniel, 2015), technological developments and Internet usage. In addition to
traditional learning methods, blended and online learning methods have also become a
challenge for many education providers worldwide. Managing the process of learning and
teaching through information and communication technology (ICT), including online learning
resources (OLR) has become standard practice in many institutions (Anshari, Alas, Yunus,
Sabtu, & Hamid, 2016). Online resources address to a large spectrum of information available
on the Internet including texts, videos, images, journals, case studies, databases and
curriculums (Smith & Rose, 2002). Learning analytics can improve learning and teaching
practices by having a good comprehension into the learning process of students to define
learning strategies, and as well enabling personal learning activities (Macfadyen, Dawson,
Pardo, & Gašević, 2014). In higher education, the users, namely students, teachers,
administrators and developers/researchers, utilize the success of students, teachers, and
institutions by collecting and analyzing student, departmental and research data with big data
and data mining tools.
In addition to the technological developments regarding learning environments (online or
face-to-face), departments in higher education institutions have to prepare individuals in a
broader sense according to the needs of the sector they will work in. Big data analytics and
related technologies have been developing very rapidly in the last decade. However, as
technology, tool and applications continue to progress, it is often found that the static nature
of the formal curriculum does not meet the requirements. In this study, articles conducted on
big data analytics in higher education were reviewed in order to determine the subjects of big
data analytics in higher education and examine curriculum developments. This paper is
divided into five main parts. In the following section, namely section 2, the basics and
characteristics of big data are explained. In section 3, the conceptual model of educational big
data analytics, student success with respect to big data, and applications in learning and
educational environments are detailed. In section 4, the methodology of the present study and
the selection criteria of the articles are given. Finally, in the last section, the findings regarding
big data in higher education and the key points of the articles related to curriculum
development are discussed.

2. BIG DATA
Many organizations use different kinds of data analysis solutions for decision-making to
achieve their operational and strategic goals. How data is stored and analyzed has changed
because the nature of the data available in the organizations has changed. It is challenging to
manage the new type of data that is unstructured and complex.
The new types of data that are growing very fast and from different sources are not sufficient
with traditional database systems. It is evident that the exponential growth of data has brought
about tremendous changes in data access, storage and processing in business and therefore,
database systems. Big data analytics is an analytical method that can turn unstructured data
into useful patterns and information.

82
 Big Data Analytics in Higher Education: A Systematic Review
IUYD’2020 / 11(2)

Manyika et al. (2011) defined big data as data that is too big and moves too fast, thus exceeding the
processing capacity of conventional database systems. Storing, managing and analyzing large data
sets with different structures requires innovative technologies and techniques (Daniel, 2015).
Davis and Patterson (2012) referred to big data as data that is too large to be analyzed by
conventional database protocols such as structured query language (SQL). Douglas (2001)
determined the three most common properties of big data as volume, velocity and variety in
Gartner's report. Given below are the fundamental characteristics of big data (Singh & Singh,
2017; Daniel B., 2015; Zikopoulos, Eaton, deRoos, Deutsch, & Lapis, 2012; Lohr, 2012):
 Volume – is the size of the data consisting of terabytes or petabytes. A large amount of
data is difficult to store, transfer and analyze.
 Velocity – is the speed of the data which is generated. Decision-makers want the
information to provide data in a fraction of a second in real-time. (e.g., status updates,
likes and shares on social media)
 Variety – refers to different data formats, data semantics and data structures like audio,
images, sensor data and weblogs.
 Veracity – means the accuracy or truth of the data.
 Value – refers to the ability to analyze data and provide a better understanding of the
various key areas.
 Verification – refers to data verification and security.

3. BIG DATA IN EDUCATION

Managing, tracking and controlling learners, courses, grades, degrees, certificates, institutions
and learning providers requires a content management system. Educational environments
involve different groups of users and these users have knowledge from a wide range of
perspectives with respect to their objectives, vision and mission (Margo, 2004).
Romero and Ventura (2010) suggested five groups of users for educational environments:
students, educators, course developers, organizations/learning providers and administrators.
Siemens and Long (2011) reported two types of analytics: (1) Learning analytics, which include
course-level and departmental level and (2) academic analytics, which include institutional,
regional, national, and international level. Higher education can utilize big data analytics for
students, educators, administrators and course developers.
Institutions can benefit from big data (Figure 1):
 For students, by personalizing learning, planning learning activities, recommending
courses, activities and resources.
 For educators, by analyzing student behavior, predicting student performance and
grouping and modeling students.
 For administrators, by organizing resources, enhancing educational programs and
evaluating teachers and curricula.
 For course developers, by evaluating courseware, improving student learning,
constructing student models and tutor models.

83
Aytaç, Z., & Bilge, H. Ş.
IUYD’2020 / 11(2)

Figure 1. Big data scopes for four users in higher education (Romero & Ventura, 2010)
Daniel and Butson (2013) aimed to find out the guidelines of Big Data within universities and
developing frameworks for data aggregation, collection and develop a data set that relates
with end-users. The end users are students, instructors, policy and researchers. They
suggested a conceptual framework for identifying big data analytics in higher education
(Figure 2). The framework consists of four components, namely learning analytics,
information technology analytics, academic analytics, institutional analytics. The definitions
of the four components are as given below:
 Learning Analytics: is collecting, measuring, analyzing and reporting the data
regarding students and their circumstances, with the intend of understanding and
improving their learning and the region in which it results (Siemens & Long, 2011).
 Institutional Analytics: analyses operational data to support effective decision making
at an institutional level like instructional analytics, assessment policy analytics and
structural analytics.
 Information Technology Analytics: uses performance data, which supports the
examination of technology, tools, processes, progressing data standards, policies and
organizational synergies.
 Academic/Program Analytics: includes information regarding programs and
performance challenges.

84
 Big Data Analytics in Higher Education: A Systematic Review
IUYD’2020 / 11(2)

Figure 2. Conceptual model of educational big data analytics adapted from Daniel &
Butson (2013)

3.1. Big Data and Student Success

Today, student’s activity on cell phones, tablets, search engines, social networks and GPS
navigators creates a tremendous amount of information, often in real-time. When and where
students shop, eat and engage in activities and lectures can be tracked with the use of student
identification cards. Course management software records what materials student access and
how long they engage with them. Big data creates knowledge for higher education including
the potential to develop customized learning experiences (Lane & Finsel, 2014).
Student success is a result of a complex interacting of many factors such as curriculum,
background, funding, testing style, class size and school size. IBM defined some categories to
improve student performance by using data in higher education in a white paper. These
categories are given below (IBM Software Group, 2001):
1. Measuring and monitoring student achievements
2. Reporting student achievements by levels such as economic status, gender and language
proficiency
3. Identifying anomalies for early intervention
4. Specifying potential by revealing patterns for individual student performance
5. Preventing abandonment by building student community and strengthening
relationships between teachers and students
6. Defining and improving key attributes of good instructors
7. Examining standardized testing to balance performance
8. Testing and evaluation of curricula

85
Aytaç, Z., & Bilge, H. Ş.
IUYD’2020 / 11(2)

3.2. Applications in Learning

Collecting and analyzing data has changed learning and teaching strategies. Information on
what students do, such as whether they attend lectures and how they perform, is important to
evaluate their particular strengths and weaknesses.
A lot of methods have been used for educational environments that have been analyzed
through data mining and big data. Baker and Yacef (2009) suggested four significant methods,
namely improvement of student patterns, working on the pedagogical support, discovering
domain models and scientific research into learning, for educational data mining.
Romero and Ventura (2010) determined the following categories of application for main
educational tasks:
 Analysis and visualization of data: Instructors and course developers can obtain
overall information about students and resolve the course activities of students to
understand student's learning. The purpose of the analysis and visualization of data is
to support decision making and create useful information.
 Feedback for supporting educators: The purpose of providing feedback to assist
teachers, contributers and management team on giving a decision is to develop
learners’ insight and arrange educational resources more productively.
 Guidance for students: The purpose of guidance is to make recommendations to
student regarding new courses by analyzing their personalized activities.
 Predicting student's performance: The purpose of predicting a student's performance
is to estimate the undetermined value of a variable that identifies the student. Student’s
interaction with other instructors and learners in a learning environment can be
analyzed and predicted their performance.
 Student modeling: The purpose of student modeling is to create models, including
learners’ knowledge and skills, with characteristics like satisfaction, motivation,
affective status and learning styles.
 Pointing undesirable student behavior: The purpose of pointing undesirable student
behavior is to determine the students who show extraordinary attitude like low
motivation, erroneous actions, cheating, playing games, academic failure and
dropping out.
 Grouping students: The purpose of grouping students is to create groups/clusters by
customizing their features and personal characteristics. Instructors build personalized
learning systems, promote active group learning and ensure applicable content by
grouping the students.
 Social network analysis: The purpose of social network analysis is to analyze the
relationships between individuals. A group of people or an organization who are
related by social in common such as friendship, collaboration or informational sharing
is described as a social network (Freeman, 2004). In educational environments, there
are different methods for social network analysis. Collaborative filtering is the most
common method for mining social networks.

86
 Big Data Analytics in Higher Education: A Systematic Review
IUYD’2020 / 11(2)

 Developing concept maps: It is a conceptual graph that demonstrates relationships

between concepts and states the hierarchal structure of knowledge (Novak & Canas,
2008). Association rule mining and text mining have been used to build concept maps.
 Constructing courseware: The purpose of constructing courseware is to support
educators in the developing process of courseware and learning contents.
 Planning and scheduling: The purpose of planning and scheduling is to improve the
conventional educational process by suggesting students with planning, course
scheduling, future courses, developing curriculums, helping in the admission
processes and planning resource allocation.

3.3. Learning Environments

Technology has been applied to learning for many years and learning environments have
evolved quickly with online and mobile learning, learning management systems, tools and
technological developments. Bersin (2018) put forward the term ‘digital learning’ in his article
titled ‘The Disruption of Digital Learning: Ten Things We Have Learned’, which refers to
“delivering learning to where people are”. Digital learning is identified as a ‘way of learning’ not a
‘type of learning.’ According to Bersin, from traditional learning to e-learning, blended learning,
talent-driven learning and continuous learning have evolved extremely fast. In digital
learning, traditional learning management systems are no longer the center of learning. Micro-
learning platforms support learners at any time and enable them to reach course contents
everywhere. The next step is intelligent learning, which is personalized, intelligent and
machine-driven (Bersin, 2018). Artificial intelligence-based learning will make a significant
contribution to education on activities such as student needs, grading, course improvements,
automated tutors and feedback in future learning environments.
There are a variety of educational learning environments like traditional classrooms, online
learning, mobile learning, blended learning, digital game-based learning and gesture-based
learning (Figure 3). In addition, there are a wide variety of educational systems like learning
management systems, learning object repositories, social networks, forums and virtual
environments. Processing all data provided by different educational systems and
environments can be resolved by using big data analytics and data mining techniques.

Blended
Learning

Traditional
Learning
Online
Learning

Learning
Environments

Gesture
Based Mobile
Learning Learning

Game
Based
Learning

Figure 3. Types of learning environment

87
Aytaç, Z., & Bilge, H. Ş.
IUYD’2020 / 11(2)

3.3.1. Face to Face (Traditional) Learning

In classroom environments, students interact with the instructor through face-to-face contact.
Data collected in classroom environments regarding student’s performance, curriculum
(Romero & Ventura, 2010), attendance, grades, instant feedback can be used as a raw data. In
addition, the profile of mood states can be collected in the classroom and analyzed with
various statistical techniques. Data gathered in the classroom environment is not as large as
the data gathered in online learning environments. Thus, it is not very sufficient to use big
data analytics for data that has been created in traditional learning environments.
3.3.2. Blended Learning
Blended learning is composed of face-to-face interaction and web-based technology. Blended
learning environments do not have only one source for gathering information, thus it is
difficult to implement learning analytics for blended learning environments. Blended learning
combines different types of technologies integrated with face-to-face classroom activities
(Picciano, Big Data and Learning Analytics in Blended Learning Environments: Benefits and
Concerns, 2014).
Picciano (2014) divided the concept of blended learning into four groups and emphasized that
they should not be considered as a limiting and absolute declaration.
 Minimal Technology-Face to Face Classroom: Students meet face-to-face. The
instructor uses basic technology like web for e-lectures or e-mail.
 Technology Infused-Face to Face Classroom: Students meet face-to-face. The instructor
uses technology like tutorials, digital videos and simulations.
 Minimal Technology-Online Environment: Students meet online. The instructor uses
basic technology, like electronic bulletin boards.
 Technology Infused- Online Environment: Students meet online. The instructor uses
multiple synchronous and asynchronous technologies like blogs, wikis and interactive
video conferencing.
3.3.3. Online Learning
E-learning is a term that refers to technology-supported learning rather than other terms like
online learning, web-based learning, and technology-mediated learning and distributed
learning (McGill & Klobas, 2009). Online learning changed the way of teaching and learning
that emerged in the 1990s and early 2000s. Institutions now offer their academic programs
online, and millions of students are enrolled in online programs (Picciano, Big Data and
Learning Analytics in Blended Learning Environments: Benefits and Concerns, 2014).
New methods for collecting and processing data on course and student activities have been
developed for online learning environments. Institutions have access to large data sets to
analyze the data, and there is an exponentially increasing amount of online student data to
analyze (Swain, 2013). With online courses, data is gathered for each student transaction.
Students use course assessment systems, blogs, discussion boards, and thus generating
thousands of transactions per course. Analytics is used for this data, which is collected in real-
time and analyzed to suggest courses of action.

88
 Big Data Analytics in Higher Education: A Systematic Review
IUYD’2020 / 11(2)

3.3.4. Mobile Learning

M-learning is the mobile and communication technology used for teaching and learning in
educational institutions that both instructors and students can benefit from (Shorfuzzamana,
Hossain, Nazir, Muhammad, & Alamri, 2019). Mobile learning enables students to make use
of their mobile devices to access learning materials like lecture notes and slides and
informative videos from anywhere and at any time. Mobile learning also gives educators more
mobility and flexibility for the creation of field learning.
According to Statista’s January 2018 data, the globally mobile population was 3.7 billion
unique users. In 2019, 63.4% of the global mobile phone users accessed the Internet from their
mobile devices (Figure 4). In 2021, worldwide mobile data traffic is expected to reach 47% of
the growth rate. The increasing number of mobile phone users and those accessing the Internet
from mobile devices shows that mobile learning will become crucial in higher education and
attract more and more users. One of the advantages of mobile learning is reducing operating
costs for institutions as students bring their own devices.

Figure 4. Mobile phone Internet user penetration worldwide from 2014 to 2019
(Statista.com)

3.3.5. Digital Game-Based Learning

The usage of the Internet and communication technology itself are not enough to motivate
students. New learning types that correspond better with their interests and habits should be
considered to attract students' attention. Within this context, computer games and digital
games may be the answer (Prensky, 2003).
Eck (2016) identified three factors of widespread public interest in games as a learning
perspective. The first factor is that digital game-based learning is more popular day by day,
and researchers tend to conduct game-based learning. The second factor is that the new
generation is disconnected from traditional instructions. They have visual skills that are
compatible well with digital games, want quick and frequent interactions with content and

89
Aytaç, Z., & Bilge, H. Ş.
IUYD’2020 / 11(2)

need multiple streams of information. The third factor is that the popularity of digital games
is increasing (Eck, 2006).
3.3.6. Gesture-Based Learning
Users interact with computers and tools more directly through the use of movements and
motions like body movements, facial expressions, finger flips, eye movements, gestures and
speech with gesture-based devices (Johnson, Adams, & Cummins, 2012).
The Horizon report has indicated that there are new opportunities in learning by using
gesture-based devices as an emerging technology. Innovative teaching and learning with
gesture-based systems are increasingly used in the fields of special education, mathematics,
physics, physical therapy, music, arts, science, social development and literacy (Johnson,
Levine, Smith, & Stone, 2010).

4. METHOD
In this systematic literature review, articles conducted on the subjects of big data in higher
education and curriculum development in higher education were selected. In the literature
review, the following criteria were used to select the articles:
 Being related to big data in higher education.
 Having used the Scopus database for research.
 Having been published between 2010 and 2020.
 Having been published in English.

Figure 5. Article Selection Process

90
 Big Data Analytics in Higher Education: A Systematic Review
IUYD’2020 / 11(2)

The following steps were used for the selection of the research material (Figure 5):
1. The keywords ‘big data’ and ‘higher education’ were used. As a result, a total of 269
relevant articles were found. Only open access articles were selected, thus, the number
of articles decreased to 62. Non-related articles were also eliminated. In the end, 40
articles were examined within the scope of this study.
2. The search was conducted in the title, abstract and keywords field of the Scopus
database.
3. The document type was selected as article. Dissertation and book chapters were
excluded, while articles in the final stage of publication were included
4. The keywords were sorted by relevance with the Scopus Advanced Search.

5. FINDINGS
The article selection process and the number of articles included in each step according to the
criterion are shown in Figure 5. After the articles that included the keywords “big data” and
“higher education” and those that were in the final publication stage were selected a total of
269 articles were determined. These articles were then screened to select those that were full
text and as a result 81 articles were obtained. Then, these articles were examined in terms of
title, abstract and keywords. The articles discussing big data analytics with regards to any
sector other than higher education were excluded. Those discussing higher education within
the scope of different approaches than big data analytics were also excluded. As a result, a
total of 40 articles were included in this review.
The literature included in this review mainly covered teaching and learning analytics, distance
learning and the challenges and opportunities of big data in higher education. Other articles
were related to curriculum development, ethics and privacy, assessment, adoption,
visualization, education policy and predictive models. In total 12 of the reviewed articles were
regarding learning and teaching analytics. It was determined that in these articles the most
used methodologies were literature review or framework development and model designing.
In addition, case study and thematic analysis had been used as the methodology of these
articles. A total of six articles were related to distance learning. Distance learning was also
referred to as online learning or e-learning in the articles. Case study, review, model designing,
framework development, clustering algorithm and chaos optimization methods had been
used in the articles related to distance learning. The third most mentioned subject regarding
big data in higher education was challenges and opportunities. All of the reviewed articles
and their methods, subject areas, titles, authors and publishing years are shown in Table1.

91
Aytaç, Z., & Bilge, H. Ş.
IUYD’2020 / 11(2)

Table 1. Big data in Higher Education Subject Areas and Methods

Number
Subject
of Method Article Titles Author-Year
Areas
Articles
1. Uncertainty in big data analytics: survey, (Hariri, Fredericks,
opportunities, and challenges & Bowers, 2019)
2. Big Data and analytics in higher education:
Opportunities and challenges
3. The Dynamic Landscape of Higher Education: The (Mahroeian &
Role of Big Data and Analytics Daniel, 2016)
Challenges / Literature
6 (Li, Huang, & Zhou,
Opportunities Review 4. Impacts on Statistics Education in Big Data Era
2018)
5. Opportunities and challenges for big data analytics (Attaran, Stark, &
in US higher education: A conceptual model for Stotler, 2018)
implementation
6. Big Data Management, Data Science and Data (Gokul,
Analytics: What is it and Where— An Educational in Sundararajan, &
Indian Perspective Paul, 2019)
(Prinsloo, Archer,
1. Big(ger) Data as Better Data in Open Distance
1. Case Study Barnes, Chetty, &
Learning
Zyl, 2015)
2. Clustering 2. Research on Cloud Computing and Its Application (Zhang, Li, & Hao,
Algorithm in Big Data Processing of Distance Higher Education 2015)
(Mehmood, Alam,
Distance 3.Framework 3. UTiLearn: A Personalised Ubiquitous Teaching and Albogami, Katib,
Learning Development Learning System for Smart Societies Albeshri, &
(Online 6 Altowaijri, 2017)
Learning / 4. Big Data Emerging Technology: Insights into
4. Model
E-Learning) Innovative Environment for Online Learning (Huda, et al., 2018)
Designing
Resources
5. Literature 5. Understand, develop and enhance the learning (Sedkaoui &
Review process with big data Khelfaoui, 2019)
6. A cognitive learning model in distance education of
6. Chaos (Wen, Zhang, & Shu,
higher education institutions based on chaos
Optimization 2019)
optimization in big data environment
1. Business Intelligence and Big Data in Higher
1. Qualitative
Education: Status of a Multi-Year Model Curriculum (Gupta, Goul, &
&
Development Effort for Business School Dinter, 2015)
Quantitative
Undergraduates, MS Graduates, and MBAs
2. Sustaining Employability: A Process for Introducing
Curriculum Clod Computing, Big Data, Social Networks, Mobile (Bologa, Lupu, Boja,
4 2. Case Study
Development Programming and Cybersecurity into Academic & Georgescu, 2017)
Curricula
3. Qualitative
3. Measuring the promise of Big Data syllabi (Friedman, 2018)
(Survey)
4.Framework 4. Data Analytics Research-Informed Teaching in a
(Lu, 2020)
Development Digital Technologies Curriculum
1. The Evolution of Big Data and Learning Analytics in
1. Review (Picciano, 2012)
American Higher Education
2. Case Study 2. Application of Learning Analytics in University (Kim, Hue, & Shin,
Mathematics Education 2016)
Teaching and
3. Thematic 3. Innovative Teaching In Higher Education: The Big
Learning 12 (Huda, et al., 2016)
Analysis Data Approach
Analytics
(Lodge, Alhadad,
4. Inferring Learning from Big Data: The Importance of
4. Review Lewis, & Gasevic,
a Transdisciplinary and Multidimensional Approach
2017)

92
 Big Data Analytics in Higher Education: A Systematic Review
IUYD’2020 / 11(2)

Table 1. (Continued)
5. Conceptual
5. Impacting Big Data analytics in higher education (Laux, Li, Seliger, &
Research
through Six Sigma techniques Springer, 2017)
Design
6. Model 6. Understanding Modern Learning Environment
(Huda, et al., 2018)
Designing (MLE) in Big Data Era
7. A Framework for Managing and Analyzing Big Data
7.Framework (Kamal & Dave,
in Indian School Education System with Reference to
Development 2019)
Jammu & Kashmir
8. A Comparative Study on Big Data Applications in (Altaye & Nixon,
8. Review
Higher Education 2019)
(Moscoso-Zea,
9. 9. A Hybrid Infrastructure of Enterprise Architecture
Castro, Paredes-
Infrastructure and Business Intelligence & Analytics for Knowledge
Gualtor, & Lujan-
Design Management in Education
Mora, 2019)
10. Systematic 10. Exploring Data Driven Youth Character Education
Literature Frameworks: A Systematic Literature Review on (Baiocchi, 2019)
Review Learning Analytics Models and Participatory Design
11. 11. Personalized Learning Environment in Higher
(Tulasi & Suchithra,
Framework Education through Big Data and Blended Learning
2019)
Development Analytics
(Klochkova, Serkina,
12. The Digitalisation of the Economy and Higher
12. Review Prasolov, &
Education
Movchun, 2020)
1. Review/ 1. Ethical Considerations in the Practical Application of
(Fynn, 2016 )
Discussion the Unisa Socio-Critical Model of Student Success
(Reidenberg &
Ethics / 2. Review 2. Achieving big data privacy in education
3 Schaub, 2018)
Privacy
3. Learning analytics and higher education: a proposed
3. Model
model for establishing informed consent mechanisms (Jones, 2019)
Designing
to promote student privacy and autonomy
Education Education Policy Research in the Big Data Era:
Policy and 1 Review Methodological Frontiers, Misconceptions, and (Wang, 2017)
Challenges Challenges
1.Weighted
Multi-
1. Be the Data: Embodied Visual Analytics (Chen, et al., 2017)
dimensional
Scaling
Visualization 2
2. Mixed
(Venkatraman,
Method 2. Visualization and Experiential Learning of
Overmars, & Wahr,
(Survey, Self- Mathematics for Data Analytics
2019)
assessment)
1. Model (Shah & Choksi,
1. Big Data Analytics Model for the Education Sector
Designing 2019)
Adoption 2
2. Emerging Trends and Future Perspective of Human (Suhasini & Kumar
2. Review
Resource Reskilling in Higher Education N , 2019)
1.Framework
Development 1. Big Data Technology-Enabled Analytical Solution (Khan, Liu, Shakil, &
with R, for Quality Assessment of Higher Education Systems Alam, 2019)
BigQuery
(Esomonu,
Assessment 3 2. Qualitative 2. Assessment big data in Nigeria: Identification,
Esomonu, & Eleje,
Case Study generation and processing in the opinion of the experts
2020)
3. Value Creation of Big Data Utilization: The Next
3. Qualitative (Dapiton & Canlas,
Frontier for Productive Scholarship among Filipino
Case Study 2020)
Academics
Predictive Qualitative “We called that a behavior”: The making of
1 (Whitman, 2020)
Models Case Study institutional data

93
Aytaç, Z., & Bilge, H. Ş.
IUYD’2020 / 11(2)

Four articles carried out on curriculum development were also reviewed. One of them
provided a new curriculum model for Business Information Systems undergraduate, MS and
MBA students. Gupta, Goul and Dinter (2015) brought together faculty, students and industry
experts to add appropriate elective courses to the existing curriculum using Krathwohl’s
revised taxonomy. They used a multi-methodological approach through interviews, surveys,
focus groups and literature reviews. Krathwol’s revised taxonomy uses two dimensions,
namely knowledge and cognitive process, to the identify learning outcomes in a curriculum.
They evaluated Krathwohl’s two dimensions on the BI topics in undergraduate, MS and MBA
curricula. They developed BI topics across three levels of BI model curricula. Bologa et al.
(2017) introduced an academic curriculum including topics such as cloud computing, big data,
social networks, mobile programming and cyber security for non-technical students. Their
study was funded by the European Union and involved 61 experts including professors,
students, company representatives and technical staff members. After their pilot test, two
partner universities updated their undergraduate and graduate programs. Their study found
that non-technical students studying business, finance, economics, statistics, marketing and
similar disciplines provided good feedback and showed interests in the new curricula.
Universities could add these topics to the curricula of their undergraduate and graduate
programs.
Friedman (2018) examined the content of Big Data syllabi and the major topics covered in these
syllabi across different academic institutions in the USA. A total of 35 syllabi were collected
from both private and public universities and most were offered in the field of Information
Technologies, namely Computer Science, Engineering and Information Science. In addition,
the field of Business offered courses on big data too. The eight most popular topics were
determined as Big Data Infrastructure (%56), Data Driven Application Systems (%49), Hadoop
MapReduce and Spark, R and Python, Data Mining Models (%41), Data Sources, Machine
Learning, Statistical Analytics, Predictive Analytics and Visualization. As a result of the study
it was determined that there was a lack of standardization with regards to the textbooks,
resources and core subjects of big data. Lu (2020) introduced a data-driven analytical
framework that provided the architecture for the development of a data analytics curriculum.
In the study, a data analytics pathway to evaluate the curriculum from a teaching, learning
and assessment perspective was put forward. The area of curriculum development on big data
analytics has mostly been aimed at non-technical students, especially business students in
higher education. However, it has been made clear that big data analytics are needed in many
departments. Analytical abilities and skills should be clearly identified according to the
expectations of the industry and big data analytics should be included in the curriculum of
different departments of universities.

6. CONCLUSION
Big data analytics plays an important role in higher education. In this study, big data and its
characteristics were summarized. Four stakeholders, namely students, educators,
administrators and course developers, and their gains were discussed by using big data
technologies. Planning learning activities, recommending courses, analyzing student
behavior, predicting student performance, grouping and modeling students, enhancing
educational programs, evaluating teachers, curricula and courseware, improving student

94
 Big Data Analytics in Higher Education: A Systematic Review
IUYD’2020 / 11(2)

learning and constructing student models and tutor models are the critical benefits for the four
stakeholders. The conceptual model of educational big data analytics was also reviewed and
discussed. This study also examined how big data technologies contribute to learning analytics
and student success. The different types of learning environments such as traditional
classrooms, online learning, mobile learning, blended learning, digital game-based learning
and gesture-based learning were also briefly mentioned in a framework.
Big data analytics and related technologies have been developing rapidly in the last decade.
However, formal curricula do not meet the industry requirements. In this study, 40 articles on
big data analytics in higher education were systematically reviewed in order to determine the
areas of big data analytics in higher education and examine curriculum development studies.
Based on the findings of the literature review, the most published articles on big data analytics
in higher education were in the field of learning and teaching analytics. Literature review and
framework development methods had been used in most of these articles. The second and
third most published articles on big data in higher education were in the field of online
learning and the challenges and opportunities of big data in higher education. In addition, it
should be noted that there were not many published articles on curriculum development.
Based on the findings of the literature review, it can be said that the area of curriculum
development on big data analytics has mostly been aimed at non-technical students in higher
education. However, it has been determined that there is a need for big data analytics in many
degrees as well as information systems.

REFERENCES
Altaye, A. A., & Nixon, J. S. (2019). A Comparative Study on Big Data Applications in Higher
Education. International Journal of Emerging Trends in Engineering Research, 7(12), 739-745.
Anshari, M., Alas, Y., Sabtu, N. P. H., & Hamid, M. S. A. (2016). Online Learning: Trends,
Issues and Challenges in the Big Data Era. Journal of e-Learning and Knowledge
Society, 12(1), 121-134.
Attaran, M., Stark, J., & Stotler, D. (2018). Opportunities and Challenges for Big Data Analytics
in Us Higher Education: A Conceptual Model for Implementation. Industry and Higher
Education, 32(3), 169-182.
Baiocchi, R. R. (2019). Exploring Data Driven Youth Character Education Frameworks: A
Systematic Literature Review on Learning Analytics Models and Participatory Design.
Estudios Sobre Educacion, 37, 179-198.
Baker, R. S., & Yacef, K. (2009). The State of Educational Data Mining In 2009: A Review and
Future Visions. JEDM| Journal of Educational Data Mining, 1(1), 3-17.
Bersin, J. (2018, 03 31). https://joshbersin.com. Retrieved 11 26, 2018, from
https://joshbersin.com: https://joshbersin.com/2017/03/the-disruption-of-digital-
learning-ten-things-we-have-learned/

95
Aytaç, Z., & Bilge, H. Ş.
IUYD’2020 / 11(2)

Bologa, R., Lupu, A. R., Boja, C., & Georgescu, T. M. (2017). Sustaining Employability: A
Process for Introducing Cloud Computing, Big Data, Social Networks, Mobile
Programming and Cybersecurity into Academic Curricula. Sustainability, 9(12), 2235.
Chen, X., Self, J. Z., House, L., Wenskovitch, J., Sun, M., Wycoff, N., & North, C. (2017). Be the
Data: Embodied Visual Analytics. IEEE Transactions on Learning Technologies, 11(1), 81-
95.
Daniel, B. (2015). Big Data and Analytics in Higher Education: Opportunities and
Challenges. British Journal of Educational Technology, 46(5), 904-920.
Daniel, B. K., & Butson, R. (2013). Technology Enhanced Analytics (TEA) in Higher Education.
International Association for the Development of the Information Society, 89-96.
Dapiton, E. P., & Canlas, R. B. (2020). Value Creation of Big Data Utilization: The Next Frontier
for Productive Scholarship among Filipino Academics. European Journal of Educational
Research, 9(1), 423-431.
Esomonu, N. P. M., Esomonu, M. N., & Eleje, L. I. (2020). Assessment Big Data in Nigeria:
Identification, Generation and Processing in the Opinion of the Experts. International
Journal of Evaluation and Research in Education, 9(2), 345-351.
Freeman, L. (2004). The Development of Social Network Analysis. A Study in the Sociology of
Science, 1, 687, 159-167.
Friedman, A. (2018). Measuring the Promise of Big Data Syllabi. Technology, Pedagogy and
Education, 27(2), 135-148.
Fynn, A. (2016). Ethical Considerations in the Practical Application of the Unisa Socio-Critical
Model of Student Success. The International Review of Research in Open and Distributed
Learning, 17(6).
Gokul, K., Sundararajan, M., & Paul, P. (2019). Big Data Management, Data Science and Data
Analytics: What is it and Where— An Educational in Indian Perspective. International
Journal of Innovative Technology and Exploring Engineering (IJITEE), 8(12).
Gupta, B., Goul, M., & Dinter, B. (2015). Business Intelligence and Big Data in Higher
Education: Status of a Multi-Year Model Curriculum Development Effort for Business
School Undergraduates, MS Graduates, and MBAs. Communications of the Association for
Information Systems, 36, Article 23.
Hariri, R. H., Fredericks, E. M., & Bowers, K. M. (2019). Uncertainty in Big Data Analytics:
Survey, Opportunities, and Challenges. Journal of Big Data, 6(1), 44.
Huda, M., Anshari, M., Almunawar, M. N., Shahrill, M., Tan, A., Jaidin, J. H., & Masri, M.
(2016). Innovative Teaching in Higher Education: The Big Data Approach. TOJET,
November, Special Issue for INTE 2016, 1210-1216.
Huda, M., Maseleno, A., Atmotiyoso, P., Siregar, M., Ahmad, R., Jasmi, K., & Muhamad, N.
(2018). Big Data Emerging Technology: Insights into Innovative Environment for Online
Learning Resources. International Journal of Emerging Technologies in Learning (iJET), 13(1),
23-36.

96
 Big Data Analytics in Higher Education: A Systematic Review
IUYD’2020 / 11(2)

Huda, M., Maseleno, A., Teh, K. S. M., Don, A. G., Basiron, B., Jasmi, K. A., & Ahmad, R. (2018).
Understanding Modern Learning Environment (MLE) in Big Data Era. International
Journal of Emerging Technologies in Learning (iJET), 13(05), 71-85.
IBM Software Group. (2001). Analytics for Achievement. Ottawa: IBM Canada.
Johnson, L., Adams, S., & Cummins, M. (2012). The 2012 Horizon Report. Austin: The New
Media Consortium.
Johnson, L., Levine, A., Smith, R., & Stone, S. (2010). The 2010 Horizon Report. The New Media
Consortium.
Jones, K. M. (2019). Learning Analytics and Higher Education: A Proposed Model for
Establishing Informed Consent Mechanisms to Promote Student Privacy and
Autonomy. International Journal of Educational Technology in Higher Education, 16(1), 24.
Khan, S., Liu, X., Shakil, K. A., & Alam, M. (2019). Big Data Technology-Enabled Analytical
Solution for Quality Assessment of Higher Education Systems. International Journal of
Advanced Computer Science and Applications (IJACSA), 10(6), 292-304.
Kim, D. R., Hue, J. P., & Shin, S. S. (2016). Application of Learning Analytics in University
Mathematics Education. Indian Journal of Science and Technology, 9(46), 1-5.
Klochkova, E., Serkina, Y., Prasolov, V., & Movchun, V. (2020). The Digitalisation of the
Economy and Higher Education. Space and Culture, India, 7(4), 70-82.
Lane, J. E., & Finsel, B. A. (2014). Fostering Smarter Colleges and Universities. Building a
Smarter University: Big Data, Innovation, and Analytics, 3-26.
Laux, C., Li, N., Seliger, C., & Springer, J. (2017). Impacting Big Data Analytics in Higher
Education through Six Sigma Techniques. International Journal of Productivity and
Performance Management, 66(5), 662-679.
Li, Y., Huang, C., & Zhou, L. (2018). Impacts on Statistics Education in Big Data Era. Educational
Sciences: Theory & Practice, 18(5), 1236-1245.
Lodge, J. M., Alhadad, S. S., Lewis, M. J., & Gašević, D. (2017). Inferring Learning from Big
Data: The Importance of a Transdisciplinary and Multidimensional
Approach. Technology, Knowledge and Learning, 22(3), 385-400.
Lohr, S. (2012, 02 11). The Age of Big Data. Big Data’s Impact in the World, pp. 1-5.
Lu, J. (2020). Data Analytics Research-Informed Teaching in a Digital Technologies
Curriculum. INFORMS Transactions on Education, 20(2), 57-72.
Macfadyen, L. P., Dawson, S., Pardo, A., & Gaševic, D. (2014). Embracing Big Data in Complex
Educational Systems: The Learning Analytics Imperative and the Policy
Challenge. Research & Practice in Assessment, 9, 17-28.
Mahroeian, H., & Daniel, B. K. (2016, June). The Dynamic Landscape of Higher Education: The
Role of Big Data and Analytics. In EdMedia+ Innovate Learning (pp. 1320-1325).
Association for the Advancement of Computing in Education (AACE).

97
Aytaç, Z., & Bilge, H. Ş.
IUYD’2020 / 11(2)

Margo, H. (2004). Data Mining in the E-Learning Domain. Campus-Wide Information

Systems, 21(1), 29-34.
McGill, T. J., & Klobas, J. E. (2009). A Task–Technology Fit View of Learning Management
System Impact. Computers & Education, 52(2), 496-508.
Mehmood, R., Alam, F., Albogami, N. N., Katib, I., Albeshri, A., & Altowaijri, S. M. (2017).
UTiLearn: A Personalised Ubiquitous Teaching and Learning System for Smart
Societies. IEEE Access, 5, 2615-2635.
Moscoso-Zea, O., Castro, J., Paredes-Gualtor, J., & Luján-Mora, S. (2019). A Hybrid
Infrastructure of Enterprise Architecture and Business Intelligence & Analytics for
Knowledge Management in Education. IEEE Access, 7, 38778-38788.
Novak, J. D., & Cañas, A. J. (2008). The Theory Underlying Concept Maps and How to
Construct and Use Them. Technical Report IHMC CmapTools, Florida.
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.
Picciano, A. G. (2014). Big Data and Learning Analytics in Blended Learning Environments:
Benefits and Concerns. IJIMAI, 2(7), 35-43.
Prensky, M. (2003). Digital Game-Based Learning. Computers in Entertainment (CIE), 1(1), 21-
21.
Prinsloo, P., Archer, E., Barnes, G., Chetty, Y., & Van Zyl, D. (2015). Big (Ger) Data as Better
Data in Open Distance Learning. International Review of Research in Open and Distributed
Learning, 16(1), 284-306.
Reidenberg, J. R., & Schaub, F. (2018). Achieving Big Data Privacy in Education. Theory and
Research in Education, 16(3), 263-279.
Romero, C., & Ventura, S. (2010). Educational Data Mining: A Review of the State Of The
Art. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and
Reviews), 40(6), 601-618.
Sedkaoui, S., & Khelfaoui, M. (2019). Understand, Develop and Enhance the Learning Process
with Big Data. Information Discovery and Delivery, 47(1),2-16.
Shah, B., & Choksi, D. (2019). Big Data Analytics Model for the Education Sector. International
Journal of Innovative Technology and Exploring Engineering (IJITEE), 8(12).
Shorfuzzaman, M., Hossain, M. S., Nazir, A., Muhammad, G., & Alamri, A. (2019). Harnessing
the Power of Big Data Analytics in the Cloud to Support Learning Analytics in Mobile
Learning Environment. Computers in Human Behavior, 92, 578-588.
Siemens, G., & Long, P. (2011). Penetrating the fog: Analytics in learning and
education. EDUCAUSE review, 46(5), 30.
Singh, D. S., & Singh, G. (2017). Big data – A Review. International Research Journal of
Engineering and Technology, 4(4), 822-824.

98
 Big Data Analytics in Higher Education: A Systematic Review
IUYD’2020 / 11(2)

Smith, A., & Rose, R. (2002). Essential Elements: Prepare, Design, and Teach Your Online
Course. In E-Learn: World Conference on E-Learning in Corporate, Government, Healthcare,
and Higher Education (pp. 2723-2724). Association for the Advancement of Computing in
Education (AACE).
Suhasini, B., & Kumar N., S. (2019). Emerging Trends and Future Perspective of Human
Resource Reskilling in Higher Education. International Journal of Recent Technology
and Engineering (IJRTE), 8(2S4).
Swain, H. (2013, August 5). The Guardian. Retrieved October 15, 2018, from
http://www.theguardian.com/education/2013/aug/05/electronic-data-trail-
huddersfield-loughborough-university
Tulasi, B., & Suchithra, R. (2019). Personalized Learning Environment in Higher Education
through Big Data and Blended Learning Analytics. International Journal of Recent
Technology and Engineering (IJRTE), 8(3).
Van Eck, R. (2006). Digital game-based learning: It's not just the digital natives who are
restless. EDUCAUSE review, 41(2), 16.
Venkatraman, S., Overmars, A., & Wahr, F. (2019). Visualization and Experiential Learning of
Mathematics for Data Analytics. Computation, 7(3), 37.
Wang, Y. (2017). Education Policy Research in the Big Data Era: Methodological Frontiers,
Misconceptions, and Challenges. Education Policy Analysis Archives, 25(94), 1-24.
Wen, J., Zhang, W., & Shu, W. (2019). A cognitive learning model in distance education of
higher education institutions based on chaos optimization in big data environment. The
Journal of Supercomputing, 75(2), 719-731.
Whitman, M. (2020). “We Called That a Behavior”: The Making of Institutional Data. Big Data
& Society, 7(1), 1-13.
Zhang, G., Li, J., & Hao, L. (2015). Research on Cloud Computing and Its Application in Big
Data Processing of Distance Higher Education. International Journal of Emerging
Technologies in Learning, 10(8), 55-58.
Zikopoulos, P., & Eaton, C. (2011). Understanding Big Data: Analytics for Enterprise Class Hadoop
and Streaming Data. McGraw-Hill Osborne Media.

99