Big Data and International Accreditations in Higher Education:

A Dutch – Russian Case Study

Florentin Popescu

, Roman Iskandaryan

and Tijmen Weber

HAN University of Applied Sciences, Ruitenberglaan 31, 6826 CC, Arnhem, The Netherlands

Plekhanov Russian University of Economics, Stremyannyy Pereulok, 36, Moscow, Russia

Keywords: Big Data, International Accreditation, Quality of Higher Education, University Global Competitiveness.

Abstract: This comparative study paper seeks to document how with the help of Big Data different aspects of

International Accreditations are perceived by both Plekhanov Russian University of Economics and HAN

University of Applied Sciences (Arnhem Business School), the Netherlands faculty and higher management.

This paper is looking at bringing advice and helping the chosen universities with their international

accreditations processes by demonstrating the importance of Big Data. The importance of Big Data and

International Accreditations to both universities will be accounted for in this paper. In comparison to current

research on Big Data in higher education, this work focuses on the goal of preparing the universities for future

academic international accreditations. It is a comparative study where is meant to learn from best practices

rather than to generalize and extrapolate results. On a conceptual way, this paper contributes to knowledge by

attempting to develop a strategic planning of the international accreditations process by determining the best

practices using Big Data while creating a process for internationalization to increase the universities’ global

competitiveness.

1 INTRODUCTION

Big data refers to amounts of data that are being

collected which are so enormous that they cannot be

analysed using conventional statistical techniques

(Dunham, 2014). This development has occurred

because technology is increasingly adapted so it can

effectively collect data, even if it is not directly used.

As an untapped resource, big data is becoming

increasingly valuable because it provides a very cost-

effective means of gathering data and drawing

conclusions (Dunham, 2014). Educators have also

started to take note to this development which has

opened new areas of didactic techniques and research

possibilities (West, 2012). Why not use Big Data in

helping with the International Accreditations?

According to the fourth Global Survey of

International Association of Universities 89% of

universities worldwide claim to have an institutional

policy or to have implemented internationalization

within their overall strategy, and 22% are preparing

https://orcid.org/0000-0001-6119-5567

https://orcid.org/0000-0003-4120-423X

https://orcid.org/0000-0002-4956-5892

an internationalization strategy (Egron-Polak and

Hudson, 2014). With the increase of globalization in

education, which manifests in a growing number of

foreign students and teachers, double degree

programs and joint research projects the importance

of international accreditations significantly, rises

(Iskandaryan, 2018).

The analysis of policies, institutional structure and

operation help administrators make improvements at

the management level (Daniel and Butson, 2013)

while higher education institutions are able to

determine variables affecting student retention and

program completion ( Wagner and Ice, 2012).

E-learning is already promoted as being important

because provides a myriad of benefits to students

such as flexibility and cost ease of access (Arkorful

and Abaidoo, 2015), but with data collected on the

answers students give on assignments it becomes

increasingly possible to develop algorithms that can

develop more personalized feedback (Belcadhi,

2016). A second advantage is that improving

Popescu, F., Iskandaryan, R. and Weber, T.

Big Data and International Accreditations in Higher Education: A Dutch - Russian Case Study.

DOI: 10.5220/0007572102070214

In Proceedings of the 4th International Conference on Internet of Things, Big Data and Security (IoTBDS 2019), pages 207-214

ISBN: 978-989-758-369-8

207

curricula becomes more effective. Traditional course

evaluation relies on the feedback of students, but with

new data analytics is becomes possible to uncover

how students interact with course contents (Reyes,

2015).

Big data can also be used to predict students’

performance early on which can allow teachers to

intervene and direct to attention to struggling students

(Picciano, 2014; Reyes, 2015). Finally, big data opens

up new forms of learning. Especially the area of

blended learning has a lot to gain from this. Blended

learning refers to combining online with traditional

forms of learning and this is gaining because of its

proven effectiveness (Porter et al., 2014). If blended

learning platforms are offered on a widespread basis

then the data that is gathered from this can be of major

importance when it comes to developing new classes

and understanding the behaviour of students.

Big Data analytics has also proven to be

beneficial in the area of higher education especially

in the decision-making process of institutions

(Wagner and Ice, 2012; Daniel and Butson, 2013;

Kellen, 2013).

According to Deepa and Chandra Blessie (2017),

Big Data analytics will create a number of

opportunities for the educational institution,

administrators, policy makers, educationalists and

also for the learners. These opportunities include:

1. Collaboration and comparisons among the

institutions would become more comfortable.

2. Improved knowledge flow and learning

success across the organization would be

achieved.

3. Learning effectiveness would be improved

through the self-measurement of learners and

educators

4. Cost reduction through managing financial

performance could be possible

5. The learning and academic risk and

complexity could be reduced.

These developments are especially interesting

because, if higher education institutions uses big data

effectively, they can improve their quality of

education but also experiment more leading to

research opportunities in helping with International

Accreditations.

For example, using a dashboard that integrates

class materials, teacher instructions, online exercises,

and peer feedback has much potential for not only

enhancing learning experiences, it also allows staff

and research to investigate indicators of education

quality such as student engagement with the

materials. Moreover, it also provides researchers the

opportunity to experiment with various kinds of

education techniques in a semi-controlled

environment.

Through doing so, it becomes much easier and

more effective to improve course contents which

would boost the overall quality of the education

institutions and help with International

Accreditations.

2 PROBLEM DEFINITION AND

RESEARCH DESIGN

The researchers encompass a consideration and

evaluation of the specific universities policies and

practices in relation to the theme and as well as an

evaluation of institutional responses to a range

of issues, policies and strategies concerning

international accreditations and the use of Big Data.

It positions the responses to internationalization

process of chosen universities within the policy

context that they set. It seeks to document how

universities’ management and faculty perceive

different aspects and dimensions of international

accreditations with the help of Big Data. In addition,

this paper highlights some of the major issues

in connection with institutional responses to the

impact of internationalization with respect to

responsibilities that range from being local to

international in nature.

In line with these recommendations, the

researchers chose a combination of interviews,

archives, and observations, with main emphasis on

the first two. In line with the explorative nature of the

study, the goal of the interviews was to see the

research topic from the perspective of the

interviewee, and to understand why he or she came to

have this particular perspective.

Policy and other documentation for the university

was collected on site, to supplement the primary and

secondary data gathered, when made and recorded.

For the international policy context, sources of

documentary information were used to scale the

international, national and local position on higher

education in selected universities. Several

governments and other websites were used to glean

policy and positional information. Sources referenced

in research papers were also utilized as resources

from online searches through various electronic

databases and search engines. The documentation

from institution was collected to gain insight into the

institution and the strategies and policies in place.

IoTBDS 2019 - 4th International Conference on Internet of Things, Big Data and Security

208

Sources of this information included: strategic plans;

management and academic structure charts; annual

reports; internationalization policy documents;

websites etc. These documents were the first types of

units of observation.

There are many options available for analysing

big data, but one that is clearly emerging in the field

of higher education is known as Education Data

Mining (EDM) (Romero and Ventura, 2010). In

short, this method refers to using statistics, machine-

learning, and data-mining algorithms in order to

analyse the breadth of educational data that is being

produced. Often the concept of EDM is used

interchangeably with Learning Analytics, which is

said to have the objective of understanding and

optimizing learning and the environments in which

learning occurs (Steiner et al., 2014). Because new

education techniques such as e-learning and massive

open online courses (MOOCs) are emerging (Hughes

and Dobbins, 2015), there is an increasing demand for

finding applications for this data. Although many

applications are possible, here we will only discuss

three in more detail and discuss some examples on

how these have been applied.

One of the key applications is predicting student

performance. Especially with international students it

is difficult assess whether they will be successful

because of the diversity in grading systems and the

fact that their educational and cultural background is

often unfamiliar to faculty and staff (Nghe et al.,

2005). Therefore, it is important to find other ways of

predicting the success and failure of students. Some

of the most commonly used methods are neural-

network models, Bayesian networks, and

classification algorithms (Romero and Ventura,

2010). For example, Nghe et al (2015) used decision

tree and Bayesian network algorithms to predict

student GPA with as much as 94% accuracy.

Similarly, Shahari et al. (2015) found a 98%

accuracy when using neural network analysis.

However, their naïve Bayesian analysis only yielded

a 76% accuracy. Many other examples are available

as well, but the important implication of this

technology is that it allows educators to intervene

earlier making drop-out less likely.

Another application that is used is for the

construction of more effective learning content. For

example, McCusker et al. (2013) proposed a new

adaptive educational environment where the learning

style of students is determined based on their online

behaviour which can then be used to create more

personalized learning environments. Balogh et al

(2013) on the other hand developed a method of

assessing which study materials students were most

likely to engage with. This has important applications

as it can help teachers to more effectively determine

which materials are most suitable or interesting to

students.

Finally, social network analysis is emerging

because of the fact that activity on social networks

can quickly produce a large amount of information.

Wen et al (2014), for example, were able to predict

student dropout in MOOCs by looking at social

media. Specifically, they were able to detect a

significant correlation between drop-rates and the

mood and sentiment about the course in discussion.

Another important source of information is twitter

feeds because it is very accessible to many people.

Koutropoulos et al (2014) investigated the Twitter

behaviours of students in online classes and were able

to do sentiment analyses. Twitter was also used by

participants for sharing information and

troubleshooting problems between classes. Social

networks can thus be utilized to both enhance the

learning experience and allow educators to get better

understanding of what people think of the course.

In the remaining sections we will describe and

discuss how some of the aspects regarding EDM will

be used, or already have been used, with the aim of

facilitating the process of receiving an accreditation.

Two education institutions are compared and we

show how EDM and big data analysis finds various

applications in both. Some of the problems in

gathering relevant information can be overcome

through EDM, but EDM is also used to satisfy criteria

better.

3 RESULTS AND OUTCOMES

Society is more and more characterised by global and

intercultural relationships, but also international

challenges. Due to this, higher education should have

a significant role in the society. Students should

understand, be able to work and make their

contribution to sustainable development at national

and global levels and education should provide the

prerequisites for this.

Intercultural and international dimensions are

integrated into both the formal and informal

curriculum into domestic e-learning environments by

higher education institutions. Internationalisation at

home is promoted by tools such as digital technology

and virtual mobility. Those students who cannot

benefit from physical international mobility

opportunities may use these tools to create their own

international contacts.

Big Data and International Accreditations in Higher Education: A Dutch - Russian Case Study

209

Since not all students will have the possibility to

gain international experience through mobility,

achieving intercultural understanding and

international experience at home is necessary for

students.

According to the needs of the institutions,

government agencies have provided assistance for

higher education institutions towards internationali-

sation. Internationalisation of higher education

institutions brings benefits to almost all areas of

society. Numerous organisations at various levels and

within different areas have responsibility for the

prerequisites for internationalisation and these

prerequisites are also influenced by several policy

areas. The internationalisation of higher education is

particularly influenced by certain domains of society

and related government agencies. These agencies

should support each other and move in the same

direction in order to put their efforts together. In order

to manage effectively the challenges and barriers, the

prerequisites of internationalisation must be

consolidated through inter-sectorial cooperation. The

key role in removing barriers through coordinated

efforts belongs to the Ministry of Education and

Research. The prerequisites for global cooperation

are highly influenced by the national level in relation

to international contacts. To consolidate bilateral

relationships with certain countries and to promote

Dutch research and higher education beyond the

national borders, assuming a more operational role

and coordinating the joint resources should be major

roles of the Government. Considering the

international competition, a more goal-oriented and

stronger cooperation among Dutch higher education

institutions may bring significant benefits.

A continued development by higher education

institutions may be ensured by NVAO by bringing

internationalisation to the forefront of the reviews

executed by NVAO. The international activities

of the institutions must be certified independently

and prove that their efforts are in the positive

direction.

Large data and relevant statistics must be

accessed to obtain a relevant evaluation. Tracking of

internationalisation and evaluation may be performed

using the opportunities offered by NVAO, which

includes review and statistical mandates. The

continuous efforts towards increasing

internationalisation may be supported on the basis

provided by NVAO.

According to Ahmed (2016) who explored the

factors necessary for Big Data implementation and

provided understanding how enhance these factors in

higher education accreditation using qualitative case

study; there are six key factors essential for big data

implementation in higher education accreditation:

 Security issues,

 Preserving privacy,

 Analytical skills,

 IT infrastructure,

 Top management support

 Collaborative information-sharing projects.

Now, HAN University of Applied Science is in

the process of getting accredited by the European

Foundation for Management Development for the

EPAS accreditation program. The aim of EPAS is to

evaluate the quality of business and/or management

degree programs that have an international

perspective (EFMD, 2018a). Interestingly, the

achievement of several of the criteria can be aided by

making good use of data technologies. Indeed, the

HAN is already experimenting with such

technologies, which have the potential of greatly

increasing the quality of its education.

For example, in its curriculum several forms of

blended learning are offered through the help of

digital platforms such as those made available by

Pearson and Khan Academy. When properly utilized

these programs offer a distinct set of advantages,

which fall in line with the criteria, set out by the EPAS

program.

First, there is the advantage that it helps to satisfy

the pedagogy criteria of EPAS (EFMD, 2018b, p.16)

through offering blended learning and the use of

modern technology. More significantly, however, is

the potential these technologies have for helping

students in a broader sense. Two important criteria of

the EPAS are the personal development of students

(EFMD, 2018b, p.17), and have more detailed ideas

of the quality of student work (EFMD, 2018b, p. 20).

Because with online platforms learning is done

online, much data regarding the students’ activities is

gathered. This can then potentially be used to

algorithmically generate individualized feedback,

which is important for their learning process

(Belcadhi, 2016).

Moreover, detailed statistics about the students’

performance can easily be tracked which allows

instructors to gain an overview of the progress that

students are making. This can for example allow

instructors to identify students who are struggling

early on (West, 2012), but this data also hold potential

for researchers because it opens up the possibility of

finding patterns in learning behaviour and see how

this correlates with specific characteristics of

students.

IoTBDS 2019 - 4th International Conference on Internet of Things, Big Data and Security

210

A second important advantage that new

technology brings is that it allows program review to

go more effectively. Currently, students’ reviews of

staff and courses are done using standardized

questionnaires, which are only administered a few

times a year. However, as this article is being written,

at HAN programs such as Evalytics are being piloted

which allow instructors to very quickly ask students

to answer a few simple questions in a matter of

minutes. Such technologies make it possible to assess

specific classes instead of whole courses, and it helps

to improve the performance of instructors by giving

more detailed feedback (Nunn et al., 2016). Because

the timing of such reviews is also more spread out,

there is also the advantage that it can potentially

circumvent certain biases such as selection bias which

has been found to influence course evaluation results

(Wolbring and Treischl, 2016).

Plekhanov Russian University of Economics

(PRUE) is a public higher educational institution

founded in 1907. Its main campus is located in

Moscow, and 17 other campuses are located in

Russian provinces and 5 campuses are located

abroad. Total number of students is over 53,5

thousand, including 22 thousand in Moscow. Being

one of the largest economic institutions in Russia,

PRUE considers accreditation as one of the most

valuable tools in its efforts to improve quality and

competitiveness of education. There are three types of

accreditation according to Russian Law on

Education: state, public, and professional. Providers

of the two last types can be foreign or international

organizations (companies, agencies, associations,

etc.).

Two important external factors have been forcing

leading Russian universities (about 50 out of total

650+ higher educational institutions) to obtain

different international accreditations: academic

excellence project "5-100" since 2012 and national

project "Export of education" since 2017. Both

initiatives require significant improvement of quality

of education and research, which is expected to

increase share of Russia at the international market of

education. Government of Russia decided that quality

of the education should meet international standards,

even if they are somewhat different from traditional

Russian requirements. Main reason for such

difference is historical separation of research and

teaching functions since Russian Academy of Science

was founded in 1725. Since then the Academy and its

institutions have conducted most of the research

while educational institutions has been concentrated

on teaching as their primary activity. It inevitably

affected quality of education and decreased the scope

and the number of research (and publications)

originated from Russian universities.

In 2013, PRUE adopted internationalization

concept as a part of its strategic development

statement. This concept considered international

accreditations as a primary tool for quality

development for each faculty (institution) and the

whole university. Based on negative experience of

EFMD (EPAS) accreditation attempt in 2011,

concept suggested that at the first stage (2013-2018),

most of the faculties should obtain at least one

international accreditation for its BSc or MSc

programs, and the university at the same time should

strengthen its internationalization efforts by attracting

more Russian-speaking foreign students and English-

speaking teachers and researchers. Second stage

(2018-2021) should include moderate growth in

international rankings (with higher pace of growth in

international faculty share and international students

share criteria) and new application for EFMD (EPAS)

accreditation.

It was considered that PRUE should extend the

number of BSc and MSc programs accredited by

international organization so that accreditation

process experience for different subject fields

(economics, management, marketing, finance, equity,

commerce, innovation, etc.) can be obtained.

Professional short-term programs of the university

also should undergo accreditation procedure by

professional foreign associations.

Big Data analysis has emerged as one of the

features that add value to academic programs in social

and humanitarian sciences both from content and

organizational dimensions. Partnership with the

following institutions has been established: Central

Economic and Mathematical Institute of the Russian

Academy of Science, Institute of System

Programming of the Russian Academy of Science,

and Joint Institute for Nuclear Research.

It permitted to develop new courses to BSc and

MSc programs, such as Analytics of Big Data,

Modern Programming and Methods of Statistical

Analysis, Semantic Research, Forecasting the

Dynamics of Macroeconomic and Financial Markets,

etc. Also new courses were added to the curriculum

of professional (non-degree) programs, such as Legal

Aspects of Cryptocurrency and Block-chain Projects,

Bitcoin Mining, E-Government, etc.

This new direction allows overcoming some

weaknesses mentioned in EFMD (EPAS) peer review

report of 2011 on program quality, such as "low level

of transfer of current research ideas into the teaching

of the program", "limited connections between the

corporate world and research activities", "unclear

Big Data and International Accreditations in Higher Education: A Dutch - Russian Case Study

211

research policy and relatively low quality of research

publications".

Internationalization strategy linked with Big Data

and other digital directions allowed PRUE in 5 years

to increase number of accredited programs at

European Council for Business Education from 2 to

13, as well as obtain accreditations from Chartered

Institute of Marketing (CIM), Chartered Institute of

Management Accountants (CIMA), The Association

of Chartered Certified Accountants (ACCA). In

addition, accreditation from Association of MBA's

(AMBA) was extended from MBA programs to MSc

programs. Consequently, internationalization,

inspired by international accreditation, allowed

PRUE to increase percentage of international students

from 3% in 2013 to 7,4% in 2018 and percentage of

international students from 0,5% in 2013 to 5,2% in

2018.

In 2017 as a way to improve quality of education

and a tool of quality assurance for potential

EFMD (EPAS) accreditation PRUE stated to use

individual exam score analysis of almost 50% of the

students for more than 70 disciplines with 4-6

intended learning outcomes and consisting of 12-18

topics each.

To make sure that current and prospective

curricula are up-to-date with labour market

requirements, PRUE administration requested to

develop a system for automated analysis of open data

from web-based sources, in particular, data placed on

various Internet portals (for example, integrator portal

of employment agencies) and in social networks (for

example, popular Russian social network

VKontakte).

After two years a system has been created for

monitoring and analysing the staffing requirements of

the labour market for university graduates (according

to the nomenclature of specialties of Russian higher

education). The collection and processing of data in

the system is carried out on the basis of modern

methods and technologies for obtaining information

from web-oriented sources. At the next stage,

machine-learning algorithms are used to translate

words into a vector representation. Then, offer

vectors are calculated, which makes it possible to

identify the semantic similarity of the labour market

requirements and professional competencies of

higher education, which are nothing but short text

fragments. The results are used to identify

relationships at different levels of models that

describe labour markets and higher education.

The data collection algorithm is implemented in the

form of periodically launched tasks, each of which

performs its part of working with data:

 search for new ads by keywords (job title,

employer, region, salary, list of duties, list of

requirements), which are specified as

parameters and allow to limit the subject area;

 the collection and loading of ads in the

database;

 selection of significant areas from the text of

job announcements (name of vacancy, region,

salary, requirements, duties);

 preparation of texts of labour market

requirements for further binding.

This system allows PRUE to eliminate such

accreditation weaknesses stated by 2011 EFMD

(EPAS) peer review report as "not enough

institutional corporate connections for research,

pedagogy, job placement" and "limited alumni

participation in university curriculum development".

At Plekhanov University administration, plans to

extend data analysis to its graduates in terms of their

career path, competences required and level of

competencies obtained at each stage of their career.

Such automated complex is intended to be used for

collecting, analysing and visualizing data on current

unique job vacancies of the labour market and related

data (employer location, professional requirements,

wage level, etc.). in different regions of the Russian

Federation posted on three major Russian job sites

("Work in Russia", HeadHunter, SuperJob) with the

ability to display data in the context of current

versions of different national and international

directories and classifiers. The system makes it

possible to obtain data on the number of vacancies in

the dynamics in all specialties and allows university

to use this system to assess the real needs of

employers in specialists in specific areas and

specialties, as required by international accreditations

as a proof of quality of education.

As a complimentary service, the system also able

to detect all possible connections between companies,

including foreign, which turns it into a product with

high potential for external commercial use. This

resource perhaps, has no analogues on the market and

allows potential user to solve the following tasks:

 creation a base of non-resident companies

operating in the Russian Federation,



use of all available open sources of information

(company registries, data of tax services,

customs, courts, data on leaks of information

from offshore companies),

 identification and analysis of links between

non-resident companies on the basis of various

information (managers, co-owners,

IoTBDS 2019 - 4th International Conference on Internet of Things, Big Data and Security

212

subsidiaries, address, telephone, historical

links, similarity of names and company

profiles, etc.),

 identification of final beneficiaries of non-

resident companies.

Apart from the fact that the information base on

non-resident companies, collected together from

various sources, is valuable in itself, it also provides

a unique opportunity to automate the acquisition of

new knowledge, such as connections between

companies registered in various jurisdictions of the

world.

Both Plekhanov Russian University of Economics

and HAN University of Applied Sciences (Arnhem

Business School), the Netherlands, aim at getting

international accredited. For larger institutions, the

accreditation process involves the collection and

processing of terabytes of data. The data is

heterogeneous, in content and in the way it is

captured and stored. There is unstructured data like

emails and teacher notes; structured data like forms,

surveys, and policies, and multimedia like e-Learning

modules and recorded class sessions. Presently, the

tasks for collecting evidence to verify if a

program complies with the requirement of an

accreditation body are done manually. Moreover,

some data is in digital format while the rest are

not. Data is also gathered from different sources like

staff, faculty, students and industry through emails,

surveys and interviews. The institution then analyses

the collected data and publishes a self-study report,

which is reviewed by the accreditation body.

Looking at the amount of documents that

accreditation institutions are asking, it could be

overwhelming for administrators to get them in place

and on time. It is clear that providing many of the

required documents of the various accreditation

institutions can be made much easier and

comprehensive when big data technologies are

properly used. For example, the criteria of quality

assurance is more attainable because of such

technologies. This is exemplified by the use of

Evalytics at HAN and the automated analysis system

developed at PRUE. Since trends in Big Data are not

coming to a halt, such technologies will no doubt only

become increasingly relevant in the future.

4 CONCLUSIONS AND

FURTHER RESEARCH

Data generated at higher educational institutions

satisfy the characteristics of Big Data. A university

operates various IT systems, such as course

management, human resource, student registration,

finance and institutional research. These systems

generate massive data every semester. Apart from the

structured data from the IT systems, students, staff

and faculty generate unstructured and semi-structured

data, such as Internet traffic, online and offline

activities and data emitted from sensors (Gubbi et al.,

2013).

Therefore, analysing data from higher-education

institutions, based on Big Data methods, is more

appropriate than traditional methods. Big Data and

data analytics allow researchers and industry to

analyse huge datasets and extract valuable patterns

(Reed and Dongarra, 2015).

While big data technologies have much potential

to them, it remains important to keep researching

what the effects are of utilizing these technologies on

the performance of students, instructors, and the

effectiveness of curriculum development. It would be

especially interesting to see how this increases the

likelihood of acquiring accreditation. Considering

that, the adoption of such technologies is not likely to

slow down anytime soon; this might transform the

way that education is offered and developed, and how

education research is performed.

Currently, the accreditation process works by

verifying the self-study report of universities and

compare it to evidence found by on-site visits. There

could be large discrepancies between the report and

the findings. By using different analytic tools to

analyse data and provide evidence to check if a

specific program matches the expectation of a

particular accreditation body prior to the onsite visit

REFERENCES

Ahmed, A.I., 2016. Big Data for Accreditation: A Case

Study of Saudi Universities, Journal of Theoretical and

Applied Information Technology, 91(1)

Arkorful, V. and Abaidoo, N., 2015. The role of e-learning,

advantages and disadvantages of its adoption in higher

education. International Journal of Instructional

Technology and Distance Learning, 12(1), p29-42.

Avella, J. T., Kebritchi, M., Nunn, S. G. and Kanai, T.,

2016. Learning Analytics Methods, Benefits, and

Challenges in Higher Education: A Systematic

Literature Review. Online Learning, 20(2), p13-29.

Balogh, Z., Munk, M. and Turcani, M., 2013, October.

Assessment tools and techniques for e-learning

evaluation: Usage analysis and survey sampling. In

Science and Information Conference (SAI), 2013,

(pp. 38-44). IEEE.

Belcadhi, L. C., 2016. Personalized feedback for self-

assessment in lifelong learning environments based on

Big Data and International Accreditations in Higher Education: A Dutch - Russian Case Study

213

semantic web. Computers in Human Behavior, 55,

p562–570. https://doi.org/10.1016/j.chb.2015.07.042

Daniel, B.K. and Butson, R., 2013. Technology enhanced

analytics (TEA) in higher education. In Proceedings of

the International Conference on Educational

Technologies, 29, p89-96.

Deepa, A. and Chandra Blessie, E., 2017. Big Data

Analytics for Accreditation in the Higher Education

Sector. International Journal of Computer Science and

Information Technologies, 8(3), p357-360.

Dunham, I. M., 2014. Big Data: A Revolution That Will

Transform How We Live, Work, and Think.

International Journal of Advertising, 33(1), 181–183.

https://doi.org/10.2501/IJA-33-1-181-183

EheFMD., 2018a. Process Manual. Available at:

https://efmdglobal.org/wp-content/uploads/EFMD_Gl

obal-Accrediation_EPAS-Process_Manual.pdf

EFMD., 2018b. Standards and Criteria. Available at:

https://efmdglobal.org/wp-content/uploads/EFMD_Gl

obal-Accrediation_EPAS-Standards_and_Criteria.pdf.

Egron-Polak, E. and Hudson, R. 2014. Internationalization

of higher education: Growing expectations, essential

values. IAU 4rd Global Survey Report ed., Paris:

International Association of Universities.

Gubbi, J., Buyya, R., Marusic, S. and Palaniswami, M.,

2013. Internet of Things (IoT): A vision, architectural

elements, and future directions. Future Generation

Computer Systems, 29(7), 1645-1660.

Hughes, G. and Dobbins, C., 2015. The utilization of data

analysis techniques in predicting student performance

in massive open online courses (MOOCs). Research

and Practice in Technology Enhanced Learning, 10(1),

p1-18.

Koutropoulos, A., Abajian, S. C., Hogue, R. J., Keskin, N.

O. and Rodriguez, C. O., 2014. What tweets tell us

about MOOC participation. International Journal of

Emerging Technologies in Learning (iJET), 9(1), p8-

21.

Iskandaryan, R., 2018. International accreditations as a tool

of university competitiveness improvement. XXXI

International Plekhanov Readings. Theses of PhD

students in foreign languages, p 52-56.

Kellen, V., 2013. Applying Big Data in higher education: A

case study. Cutter Consortium white paper, 13(8).

McCusker, K. A., Harkin, J., Wilson, S. and Callaghan, M.,

2013. Intelligent assessment and content

personalisation in adaptive educational systems. In

Information Technology Based Higher Education and

Training (ITHET), 2013 International Conference on

(pp. 1-7). IEEE.

Nghe, N. T., Janecek, P. and Haddawy, P., 2007, October.

A comparative analysis of techniques for

predicting academic performance. In Frontiers in

Education Conference-Global Engineering:

Knowledge Without Borders, Opportunities Without

Passports, 2007. FIE'07. 37th Annual (pp. T2G-7).

IEEE.

Picciano, A., 2014. Big Data and Learning Analytics in

Blended Learning Environments: Benefits and

Concerns. International Journal of Interactive

Multimedia and Artificial Intelligence, 2(7), p35-43.

https://doi.org/10.9781/ijimai.2014.275

Porter, W. W., Graham, C. R., Spring, K. A. and Welch, K.

R., 2014. Blended learning in higher education:

Institutional adoption and implementation. Computers

and Education, 75, p185–195. https://doi.org/

10.1016/j.compedu.2014.02.011

Reed, D.A. and Dongarra, J., 2015. Exascale computing

and big data. Communications of the ACM, 58(7), p56-

68.

Reyes, J. A., 2015. The skinny on big data in education:

Learning analytics simplified. TechTrends, 59(2), p75–

80. https://doi.org/10.1007/s11528-015-0842-1

Romero, C. and 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), p601-618.

Shahiri, A. M. and Husain, W., 2015. A review on

predicting student's performance using data mining

techniques. Procedia Computer Science, 72, p414-422.

Steiner, C. M., Kickmeier-Rust, M. D. and Albert, D., 2014.

Learning analytics and educational data mining: An

overview of recent techniques. Learning analytics for

and in serious games, 6, p61-75.

Wagner, E. and Ice, P., 2012. Data changes everything.

Delivering on the promise of learning analytics. In

higher education. Educause Review, 47(4), p33-42.

Wen, M., Yang, D., and Rose, C., 2014, July. Sentiment

Analysis in MOOC Discussion Forums: What

does it tell us? In Educational data mining.

West, D. M., 2012. Big data for education: Data mining,

data analytics, and web dashboards. Governance

studies at Brookings, 4(1).

Wolbring, T. and Treischl, E., 2016. Selection bias in

students’ evaluation of teaching. Research in higher

education, 57(1), p51-71.

IoTBDS 2019 - 4th International Conference on Internet of Things, Big Data and Security

214