ChapterPDF Available

Learning Analytics and MOOCs

Authors:

Abstract and Figures

There are new discoveries in the field of educational technologies in the 21st century, which we can also call the age of technology. Learning Analytics (LA) has given itself an important research field in the area of Technology Enhanced Learning. It offers analysis, benchmarking, review and development techniques for example in online learning platforms such as those who host Massive Open Online Course (MOOC). MOOCs are online courses addressing a large learning community. Among these participants, large data is obtained from the group with age, gender, psychology, community and educational level differences. These data are gold mines for Learning Analytics. This paper examines the methods, benefits and challenges of applying Learning Analytics in MOOCs based on a literature review. The methods that can be applied with the literature review and the application of the methods are explained. Challenges and benefits and the place of learning analytics in MOOCs are explained. The useful methods of Learning Analytics in MOOCs are described in this study. With the literature review, it indicates: Data mining, statistics and mathematics, Text Mining, Semantics-Linguistics Analysis, visualization, Social network analysis and Gamification areas are implementing Learning Analytics in MOOCs allied with benefits and challenges.
Content may be subject to copyright.
Draft originally published in: İnan E., Ebner M. (2020) Learning Analytics and MOOCs. In: Zaphiris P.,
Ioannou A. (eds) Learning and Collaboration Technologies. Designing, Developing and Deploying Learn-
ing Experiences. HCII 2020. Lecture Notes in Computer Science, vol 12205. Springer, Cham. pp. 241-254
Learning Analytics and MOOCs
Ebru İnan 1 and Martin Ebner 2
1 Educational Technology, Graz University of Technology, Graz, Austria;
einan@student.tugraz.at
2 Educational Technology, Graz University of Technology, Graz, Austria:
martin.ebner@tugraz.at
Abstract. There are new discoveries in the field of educational technologies in
the 21st century, which we can also call the age of technology. Learning Analyt-
ics (LA) has given itself an important research field in the area of Technology
Enhanced Learning. It offers analysis, benchmarking, review and development
techniques for example in online learning platforms such as those who host Mas-
sive Open Online Course (MOOC). MOOCs are online courses addressing a
large learning community. Among these participants, large data is obtained from
the group with age, gender, psychology, community and educational level differ-
ences. These data are gold mines for Learning Analytics. This paper examines
the methods, benefits and challenges of applying Learning Analytics in MOOCs
based on a literature review. The methods that can be applied with the literature
review and the application of the methods are explained. Challenges and benefits
and the place of learning analytics in MOOCs are explained. The useful methods
of Learning Analytics in MOOCs are described in this study. With the literature
review, it indicates: Data mining, statistics and mathematics, Text Mining, Se-
mantics-Linguistics Analysis, visualization, Social network analysis and Gami-
fication areas are implementing Learning Analytics in MOOCs allied with bene-
fits and challenges.
Keywords: Educational Technology; Learning Analytics; MOOCs.
1 Introduction
Learning Analytics is a research discipline that is rapidly developing, aims to analyze
and optimize learning and learning environments [1]. E-Learning Platforms such as
Learning Management Systems (e.g. Moodle) or MOOC-platforms (e.g. edx, Udacity,
Coursera etc.) have become frequently preferred tools by educators in high capacity
classes. These platforms, which are used with the purpose of supporting learning, in-
corporating technology into education, introducing information to students, and im-
proving the quality of education, need various analyzes to monitor the availability of
the system and the student's performance change. In this way, the concept of learning
analytics has emerged along with Technology-Enhanced Learning (TEL) [2].
In our age, the concept of educational technologies is becoming widespread. Teachers
and educators need to be aware of the importance of using technologies and tools to
2
increase student’s motivation and ensure their participation. New teaching skills in this
all-global education transformations should be adopted and implemented [3].
In this study scope, it is aimed to present an overview of existing learning analytics
concepts and methods strongly focused in conjunction with Massive Open Online
Courses(MOOCs). At the end of the study, a literature review about the concepts of
MOOCs and learning analytics is going to be compiled and the future tools’ function-
ality of learning analytics in MOOCs is going to be presented.
2 Introduction to Learning Analytics and MOOCs
Learning analytics term, initially stated in LAK 2011: 1st International Conference
Learning Analytics and Knowledge and used as a base by Society of Learning Analytics
(SoLAr) is defined as “the measurement, collection, analysis and reporting of data
about learners and their contexts, for purposes of understanding and optimizing learn-
ing and the environment in which it occurs” [4].
Learning is a social process that includes interactions with students, teachers, instruc-
tors and others. The instructors make an effort in their learning design to maximize
these interactions. All these preparations bring many questions as following: “How ef-
fective was the lecture? Did it meet the needs of the students? How can it be improved?
Is an update required in learning design?” etc. Large data are obtained with approaches
towards answering these questions. All these data to be used in developing teaching
and learning are statistically evaluated and analyzed with Learning analytics [5].
The first learning analytics conference that took place in Banff City, Canada in 2011,
brought together researchers from around the world to explore and develop learning
analytics [6]. Since 2011, there are education and learning platforms on the basis of
Learning analytics, with unprecedented development. Although it is a young area, there
are close relationships between Learning Analytics and Web Analytics, Educational
Data Mining (EDM) and Academic Analysis [7].
Place Fig 1 here
Fig. 1. Learning Analytics, Educational Data Mining, Web Analytics and Academic
Analytics [7].
The concept of distance education, which is method “old concept”, has undergone great
progress along with today's Internet and technology. By this means of distance educa-
tion, access information gets easy for users. Learners are positioned as persons who
access, produce, shape and analyze information individually. As access to information
becomes easier, the change to educate many people at once applied. Thus, the occur-
rence of the model called Massive Open Online Course or MOOCs was supported.
The term MOOCs has been first appeared in 2008 by Stephen Downes and George
Siemens. Subsequently, in 2011, the training videos of Stanford University professors
were published on free of charge online learning platforms. Same year, MOOCs ex-
ploded around the world; Later, Coursera, Udacity, Udemy, MITx platforms were es-
tablished. Thus showed great improvement towards [8].
3
In general, MOOCs support models, which are free learning and independent from time
and space. It also examines and follows the success and failure of the students. Moreo-
ver, it provides at least free accessibility for all participants.
Massive Open Online Course can be explained with the words of concepts in its name.
1-Massive: Massive means huge and gigantic. A large number of students participated
in the MOOCs is symbolized with this letter. Opened training can be held easily with
the participation of 100 people or with the participation of 100000 people. In addition
to the size of the number of students, with the conception of massive, outside the cam-
pus boundaries, the concept of class global class is also defined. At this juncture, learner
variations, educational material and transportation network size come into prominence
[9].
2-Open: This term symbolizes the openness to each individual with access to the Inter-
net. This is the most distinctive feature of MOOC-based education. Learners are free to
join or not to join, interact, analyze in the subjects and getting the education they would
like to learn. There are few to no prerequisites necessary to attend courses. There are
target groups addressed by courses. These prerequisites are only available in some ar-
eas, which require expertise. MOOCs comprise word of open by being mostly free of
charge [10].
3-Online: In the MOOCs model, management, data system and education are offered
entirely online. There is no physical place. All educations are actualized in the courses
which are accessible online and offered on the web [7].
4-Course: With this word, it is stated that the contents of the lectures are structured with
pedagogical approaches within the educational plan done by instructional designers.
3 Research Methods
This study aims to describe the methods, benefits and challenges of using and imple-
menting Learning Analytics in evaluating data of MOOCs. In order to support, the ef-
fective application of learning analytics in MOOCs, further clarification is required.
The trends of Learning Analytics in MOOCs will be examined and will be a guide for
future research. This research is supported by the literature review examining keywords
such as Learning Analytics and MOOCs.
It includes combinations of search terms deemed appropriate for the potential of the
study during the search. The search string used are "Learning Analytics" and "MOOCs"
and "Massive Open Online Course" and "Learning Analytics - MOOCs". After speci-
fying these search string, search queries were conducted in selected databases between
2009-2019 dates. A research, investigation and screening series, which started with
TUBibliothek Library of University search, was conducted. Afterwards, full-text search
of that search strings such as Learning Analytics and MOOCs were done in large data-
bases offering academic publications of Semantic Scholar, Web of Science, Google
Scholar, Research Gate, Scopus and Dergipark which is the academic field of research
4
that provides access to information in Turkey. In this way on this study has been inten-
sified with a comprehensive literature review to identify methods, benefits and chal-
lenges of Learning Analytics in MOOCs.
3.1 Data Collection Method
The data collection method used within the scope of the article is a thematic literature
review. The themes are defined from the revised literature and are based learning ana-
lytics on the achievements of MOOCs, which have been built over the last decade and
related to education, enabling a better theoretical understanding. The literature re-
viewed and discussed is comprehensive, the method for successful implementation is
based on relevance, taking into account the main purpose of identifying benefits and
challenges.
The titles, abstracts, keywords of the articles as a Search String was searched in that
literature databases. A temporal filter was applied from 2009 to 2019 since Learning
Analytics is a relatively new field that emerged back in recent years. This search data
collection resulted in a total number of papers as shown in Table I.
Table 1. Literature Review on Databases
Place Table 1 here
As a result, as a part of this review, it was referenced a total of 49 articles, which were
fully read in the research process and cited in the context of the review of this study
4 Results of the Literature Review: Learning Analytics &
MOOCs
Data Science is a field that allows creating knowledge from data in various shapes that
are processed or unprocessed [11]. Learning Analytics is an Educational Data Imple-
mentation Science. It is based on the fundamentals of learning analytics, computer sci-
ence, statistical calculations, data mining, machine learning, and human-computer in-
teraction [12]. MOOCs are a mine to carry out learning analytics because all the behav-
iors that occur in MOOCs are much higher and higher than the amount of behavior
recorded in traditional education [13].
If we explain it in detail, Learning Analytics provides an opportunity to examine student
behaviors in MOOCs and to maintain the positive effects of the instructors' behaviors
on learners or to clarify their concerns. In this research, methods, benefits and chal-
lenges of Learning Analytics and MOOCs are examined as well as their limitations.
Learning Analytics, which contains different disciplines such as Computer Science,
Statistics, Psychology and Education, has not only technical and statistical analysis
methods but also different analysis methods.
5
To expand research on MOOCs, Learning Analytics methods described by Khalil et al.
have been studied. In MOOCs which is one of the online learning courses, learning
analytics is carried out by such methods: data mining technique, statistics and mathe-
matics, Text Mining, Semantics-Linguistics Analysis, visualization, Social network
analysis and Gamification [14].
4.1 Data Categories
4.1.1 Data Mining
It is a method in which uses data to explore student’s learning ways that have not been
found before. It aims to bring on understanding with the available data. Emotions of
students and their effects on the performance of the processes they perform in the sys-
tem can be researched with data mining in MOOCs [15].
Data mining in e-learning is conducted with Classification and Regression Approaches.
Future behaviors and attitudes in MOOCs can be designated by analyzing and pointing
former data. Collected answers of questions in Classification are always “true” or
“false” while they are represented as digits in Regression. The correct classification
ensures obtaining correct results from data [16].
Also, Data Mining can be executed on MOOCs due to it is able to be included in e-
learning environments. It supports to improve MOOCs environments. In the scope of
this method, significant information is procured in MOOCs by using Prediction, Clas-
sification, Association Rule in Mining, Cluster and Fuzzy Logic Techniques [17][18].
4.1.2 Statistical and Mathematical
Statistical and Mathematical methods are used to observe the relationship between par-
ticipation rates and achievements by analyzing students' educational backgrounds. With
this method based on numerical data, it is also possible to inform the instructors on
increasing the student motivation, by determining the students with low participation
in education [19].
There are data about students’ behaviors and actions on MOOCs. Data such as online
durations, number of being active, visited pages, percentage of reading and watched
materials are stored on the system. The results are obtained with Statistical and Mathe-
matics methods such as Average, Mean and Standard Deviation [20].
Furthermore, this method is used with some data mining techniques while it is applied.
A method named Markov Chain, which is a statistical, and mathematics method has
been also used on examining students’ behaviors [21].
6
4.1.3 Text mining- Semantics-Linguistics Analysis
Data from user-generated content, discussion sections on forums and blogs are inter-
preted through Text mining- Semantics-Linguistics Analysis. In the examination of ed-
ucation dropout in MOOC, research and analysis that will take place in the forum and
discussion sections can reveal a real result [22].
While this method is implemented, diverse techniques are used. Summarization Tech-
nique on summarizing by reducing the length properly, Categorization Technique on
classifying technique-documents, Retrievals Technique on obtaining the valuable in-
formation inside the text, Extract Technique on picking over information and Cluster
Technique on collecting and stacking documents besides analyzing texts are utilized
[23].
4.1.4 Visualization
Another applicable method to the MOOCs is the Visualization method. With this
method, the visualization of all the data obtained enables the user and researchers to
obtain meaningful information and make analyzes through MOOCs the training per-
formed [24].
Visualization is one of the key points about applying e-learning objects for data in ed-
ucation and MOOCs. The power of visualizing data comes from the enhancement of
data’s processability and enabling explain with occurred arguments [25]. This tech-
nique is used for doing proper learning, develop brainstorming and creativity. The fol-
lowings can be shown as examples for Visualization Technique; Mind map, Concept
Map, Cognitive Map, Radial Tree, Semantic Map, Rhizome, Visual Metaphor, Tree
Structure, Argument Map and Social Map [26].
4.1.5 Social Network Analysis
Social network analysis now occupies a significant place among the Learning analytics
methods. It is a method used by many researchers to understand and optimize the learn-
ing environment. Social network analysis provides an in-depth analysis of network
structures and participates in training engagement interactions [27].
Social Network Analysis is implemented to interpret and analyze relations among the
found data in works as well as interactions in communication tools [28]. It is a technique
that is continuously growing and developing new methods and approaches. On imple-
menting this technique, Practices such as Block Modelling and Equivalence, Signed
Graphs, Structural Balance and Analysis, and Dynamic Network Analysis are utilized
[29].
4.1.6 Gamification
Gamification method increases student motivation, learning platform usage and partic-
ipation in courses and makes learning entertaining. The practice of gamification in
7
MOOCs enables students and participants to achieve success an immersive experience
with high motivation and high participation [30].
There are differences in participation and training completion levels in MOOCs and
online learning environments. Students' motivation with simple game features and their
commitment to learning processes are increasing. By the help of the secret relationship
between computers and games, it is advantageous to use the gamification method in
online learning platforms [31]. Learning for learners is available by making transactions
in processes. Learners gain ability to manage their time and speed while improving
their ability to follow. In this process, learners can experience sense of wonder, mys-
tery, fun, excitement and sadness when they are learning [32]. The most used gamifi-
cation methods in education are defined as Visual Status, Social Engagement, Freedom
of Choice, freedom to fail, Rapid Feedback and Progress [33].
4.2 Current Situations
Considering all these methods, it would not be wrong to state that the application of
Learning Analytics on MOOCs has benefits and difficulties. MOOC platforms and sim-
ilar online learning platforms are data stores. It is a data mine to perform learning ana-
lytics in MOOCs with mouse clicks, forums and discussion activities, on-the-fly and
post-test performances, entry frequency and active time, time spent on work and as-
signments, and video interactions. In this way, direct intervention can be provided to
the success of the student and the quality of education [34].
Table 2. 6 Areas of Learning Analytics and MOOCs
6 Areas of Learning Analytics and MOOCs
Areas
Description
Techniques
1
Data Mining
It is an observation oriented learning
analytics technique that contributes
to student interaction and teaching
models design[35].
Predictions
Classification
Association rule
in mining
Clustering
Fuzzy Logic
2
Statistical and
Mathematical
It is the analysis and interpretation
of quantitative data to reach infor-
mation.
Average
Mean
Standard devio-
tion
Markov Chain
8
3
Text mining- Se-
mantics-Linguis-
tics Analysis
It is a method of reaching useful in-
formation by discovering and defi-
ning meaningful ones from the texts
on the system[36].
Summarization
Categorization
Retrievals
Extract
Cluster
4
Visualization
It is a visual conversion of informa-
tion by using special engineering
techniques in original forms of
data[37].
Mind Map
Concept Map
Cognitive Map
Radial Tree
Semantic Map
Rhizome
Visual Metaphor
Tree Structure
Argument Map
Social Map
5
Social Network
Analysis
Relational bonds and behaviors are
measured, defined, analyzed and ta-
ken precautions[38].
Blockmodelling
and equivalence
analysis
Signed graphs
and structural ba-
lance analysis
Dynamic
network analysis
6
Gamification
It is used to increase the quality and
quantity of activity and training out-
puts by increasing user effective-
ness[39].
Visual Status
Social enga-
gement
Freedom of cho-
ice
Freedom to fail
Rapid feedback
Progress
Although MOOCs are among the education trends in the world today, they comprise
many challenges within. The determination of the needs of learning and the suitability
of education is very complex on the system. In general, in the statistics of MOOCs, it
occurs a low rate of fulfilment on education, despite remarkable high rate of the regis-
tered participant. The concept of learning analytics supports to solve and analyzes such
cases that are mentioned above [40].
According to the study by Khail, Taraghi and Ebner (2016), the benefits of learning
analytics in MOOCs are limitless. These are indicated as Prediction, Recommendation,
Visualization, Entertainment, Benchmarking, Personalization, Enhance Engagement,
Communication Information and Cost Saving [34].
9
Learning analytics aims to develop students' knowledge and skills with data obtained
from online learning platforms and MOOCs. When this method uses, students' learning
quality is maximized. Examining, using and analyzing the obtained data provide several
benefits for education.
Learning Analytics and MOOCs together enables students to interpret their own results
and review their performance, to instructors to affect the learning of students or student
groups in MOOCs. Moreover, they also provide an advantage to management about
learning outcomes and using personal programs [41].
With the analysis of the data, instructors can determine renewals in the curriculum and
students’ weaknesses in learning and understanding. Instructors can make educational
strategic changes over the curriculum. These renewals provide an advantage for im-
proving curriculum quality and learning potential of students [42].With the implemen-
tation of learning analytics, instructors can easily identify individual errors [43].
In this study, MOOCs and Learning Analytics concepts, methods, benefits and chal-
lenges of the implementation of Learning Analytics in MOOCs have been put forth. It
is seen that the application of Learning Analytics in online learning platforms and es-
pecially MOOC platforms are interdisciplinary studies. There is a need to operate a
comprehensive process from all sorts of inputs and outputs on MOOCs, from students
and participants to educators. There are many techniques such as Visualization, Statis-
tical and Mathematical etc. and pedagogical methods such as Gamification in order to
make learning analysis true. These methods which can be applied in MOOCs are men-
tioned. As part of the literature review, references to these methods and fields are given
in Table 3.
Table 3. 6 Areas Reference Review
Place Table 3 here
Implementations of these methods gain favors on converting large amounts of data in
MOOCs into information and quality. It provides useful information about the needs of
students, classroom interactions of teachers, educational activity and curriculum ar-
rangements. In the future, as the usage and the development of technologies advance,
new advantages and benefits will arise
4.3 Typical Examples
In the following paragraphs we would like to list a typical example for each area ac-
cording to table 2.
Data Mining: In the study conducted by Mukala et al., Learning behaviours of students
have been analyzed by examining the correlation between the students’ video course
follow-ups and success. Using the data mining technique, it is seen that the student's
video surveillance have a direct impact on performance. In addition, it has been ob-
served that behaviour studies can be developed and necessary improvements and
measures can be taken for the future with the interesting parts of the course examined
and the data of the most skipped or repeated sections [44].
10
Statistical and Mathematical: In the study carried out by Taraghi et al., Data set analysis
was performed by considering the answering time of the students and it has been deter-
mined the easiest and most difficult questions in different types. The questions were
classified as difficult, medium, easy with the K-means algorithm method. Thus, it was
concluded that the question selection algorithm will be developed with the Markov sta-
tistical analysis method which will be applied for each question and this will affect the
performance of the students [21].
Text mining- Semantics-Linguistics Analysis: In the study of Tucker and Pursel on
MOOCs, they investigated the effects of the texts produced by the students on the stu-
dent performances and outputs by using the Text mining - Semantics-Linguistics Anal-
ysis technique. According to the results of the study, it was found out that the students'
feelings had an impact on exam performance and homework. During the research, text
data was obtained via MOOCs and the data were arranged on SQL. This technique was
applied by using emotional analysis algorithms on the textual data and results were
obtained [45].
Visualization: Zhang and Yuan have worked on video recordings in MOOCs to explore
the relationship among courses. Within the scope of the study, it was seen that all par-
ticipants registered at least two courses while there was not any participant in only one
course. A visualized network diagram was applied to the relationship between courses
and learners. With the performed analysis, it was concluded that it is possible to enroll
in lectures at the same time. In this way, an environment will be created to present the
other open courses for registered participants [46].
Social Network Analysis: Kellogg, Booth and Oliver have applied the Social Network
Analysis technique in their studies in order to present a peer-assisted learning approach
in MOOCs. This method has been preferred to measure and visualize interaction pat-
terns within the scope of the study. To implement this statement, they have used the
free NodeXL template, which is an add-in to Excel. Thus, they explained the im-
portance and use of peer interaction in training prepared for educators [47].
Gamification: In their study, Vaibhav and Gupta have done Gamified and Non Gami-
fied groups on MOOCs and analyzed the differences. It was seen that the completion
rate of courses was more successful in the platforms using gamification technique. The
number of students who refused to take the final exam decreased by 14% in gamified
platforms. It is explained based on the survey results that students have fun and devel-
opments in their education by Gamification application [48].
As it is seen in these studies; learning analytics in MOOCs provides many benefits; On
the other hand, it includes ethical, legal, technological and security challenges. On this
topic some precautions should be taken on pedagogical transparency, data control and
safety.
Generally, the advantages of learning analytics in MOOCs are indicated as follows
[42]:
Determining the target course
Improvement of the curriculum
Student learning outcomes, behaviors and processes
Individualized learning
Teacher performance improvement
11
Post-educational employment.
Although learning analytics in MOOCs provides many benefits over learning, there are
some difficulties in the implementation process. The data which is obtained on the plat-
forms is not knowledge. This data should be transformed into information and
knowledge by processing, then interpreted correctly. Learning is a complicated process.
Learning also contains cultural behaviors. While learning analytics offers technical
analysis, it requires trainers to use different culturally and behaviorally educational
models in interpretation .To perform and interpret can take time on Learning Analysis.
Considering the individuality of learning, these issues can be seen as challenges.
According to Ferguson, some of these challenges [49]:
The necessity of establishing strong connections with learning science
Difficulty in understanding and optimizing learning environments and MOOCs.
Focus on students’ point of view
Not to develop and implement a clear set of ethical rules
There is no doubt that the challenges with envisaged by our age technologies and rap-
idly evolving platforms will be solved in the future. Learning analysis and MOOCs,
with contributions to education and learning, is a scientific field and it is continuously
developing.
Learning Analytics and MOOC with all their content are pioneers in education. They
will continue to be the focal point on implementing large data analysis in education and
online learning platforms.
5 Discussions
That Literature Review provides a comprehensive overview of the Learning Analytics
methods, benefits, and challenges of MOOCs. The examination of these features
showed positive contributions. However, with the literature review, it has also been
revealed from publications that the use of Learning Analytics in education has increased
over time.
This study revealed that Learning Analytics is an interdisciplinary field as suggested
by Clow (2013). Therefore, learning analytics selects and uses the most appropriate
methods and analysis techniques to achieve the goal of making education more efficient
at MOOCs. The use of an inclusive method will lead to improved learning experience
for students.
6 Conclusions
Learning Analytics is a new area and ever developing concept. In additional to this,
MOOCs with the huge data sources have an important role in applying learning analy-
sis. The state-of-the-art methods of learning analytics in MOOC are described in this
study. Data mining, statistics and mathematics, Text Mining, Semantics-Linguistics
12
Analysis, visualization, Social network analysis and Gamification areas are imple-
mented Learning Analytics in MOOCs allied with benefits and challenges. In the future,
it is expected that the implementation of learning analytics and large data will be effec-
tively used more and more in MOOCs to understand how learning is happening.
References
1. Saqr, M.: A Literature Review of Empirical Research On Learning Analytics in Medical
Education. International Journal of Health Sciences 12(5),1-6 (2018).
2. Bahçeci, F.: Öğrenme Yönetim Sistemlerinde Kullanılan Öğrenme Analitikleri Araçlarının
İncelenmesi. Turkish Journal of Educational Studies 2(1), 41-58 (2015).
3. Chang V., Gütl C., Ebner M.: Trends and Opportunities in Online Learning, MOOCs, and
Cloud-Based Tools. Springer International Handbooks of Education, Springer International
Publishing.1-19 (2018).
4. Siemens, G.: Learning Analytics the Emergence of a Discipline. American Behavioral Sci-
entist 57(10), 1380-1400 (2013).
5. Elias, T. :Learning Analytics: Definitions, Processes and Potential, https://landing.athabas-
cau.ca/file/download/43713, last accessed 2019/04/23.
6. Dawson, S., Joksimovic, S., Poquet, O., Siemens, G.: Increasing the Impact of Learning
Analytics. In Proceedings of the International Conference on Learning Analytics and
Knowledge,https://dl.acm.org/citation.cfm?id=3303784&dl=ACM&coll=DL ,last accessed
2019/04/22.
7. Khalil, M.: Learning Analytics in Massive Open Online Courses. Doctoral Thesis, Graz
University of Technology, Graz (2018).
8. Baturay, M.H.: An overview of the world of MOOCs. Procedia - Social and Behavioral
Sciences 174, 427-433 (2015).
9. Bozkurt, A.: Kitlesel Açık Çevrimiçi Dersler (Massive Open Online Courses - MOOCs) ve
Sayısal Bilgi Çağında Yaşamboyu Öğrenme Fırsatı. Açıköğretim Uygulamaları ve
Araştırmaları Dergisi 1(1), 56-81 (2015).
10. Mali,A.K. :Massive Open Online Courses,.EduInspire: An International E-Journal 3(1) 1-9
(2016).
11. Dhar, V.: Data Science and Prediction. Communication of the ACM 56(12), 64-73(2013).
12. Piety, P.J., Behrens, J., Rea, R.: Educational Data Science and The Need for Interpretive
Skills. American Educational Research Associations 27(2013).
13. O’Reily, U.M., Veeromochoneni, K.: Technology for Mining the Big Data of MOOCs. Re-
search&Practice in Assessment 9, 29-37 (2014).
14. Khail, M., Ebner, M.: What is Learning Analytics about? A Survey of Different Methods
Used in 2013-2015. Smart Learning Conference Dubai, 294-304 (2016).
15. Tucker, C., Pursel, B.K.,Divinsky, A.: Mining Student-Generated Textual Data In Moocs
And Quantifying Their Effects On Student Performance And Learning Outcomes. Comput-
ers in Education JournaL 5(4), 84 (2014).
16. Ionita, I.: Data Mining Techniques for E-Learning. Journal of Applied Computer Science &
Mathematics 10(22), 26-31 (2016).
17. Abd Elaal. S.A.E.: E-Learning Using Data Mining. Chinese-Egyptian Research Journal
(2013).
18. Lile, A.: Analyzing E-Learning Systems Using Educational Data Mining Techniques. Med-
iterranean Journal of Social Sciences 2(3),403-419 (2011).
13
19. Al-Shabandar,R.,Hussain, A.J., Liatsis,P., Keight, R.: Analyzing Learners Behavior in
MOOCs: An Examination of Performance and Motivation Using a Data-Driven Approach.
IEEE Access PP,99 (2018)
20. Chatti, M.A., Dyckhoff, A.L., Schroeder, U., Thüs, H.: A Reference Model for Learning
Analytics. International Journal of Technology Enhanced Learning (IJTEL) 4(5), 318-331
(2013).
21. Taraghi, B., Saranti, A., Ebner, M., Schön, M.: Markov Chain and Classification of Diffi-
culty Levels Enhances the Learning Path in One Digit Multiplication. In International Con-
ference on Learning and Collaboration Technologies Springer, 322-333 (2014).
22. Wen, M., Yang, D., Rose,C.P.: Sentiment Analysis in MOOC Discussion Forums:What
Does It Tell Us?.Conference: Educational Data Mining (2014)
23. Dang, S.,Ahmad, P.H.: Text Mining : Techniques and its Application. IJETI International
Journal of Engineering & Technology Innovations 1(4), 22-25 (2014).
24. Gama, S., Gonçalves, D.: Visualizing Educational Datamining Patterns. Eurographics Con-
ference on Visualization (EuroVis), United Kingdom (2014).
25. Williamson,B. :Digital Education Governance: Data Visualization, Predictive Analytics,
And ‘Real-Time’ Policy Instruments. Journal of Education Policy 31(2), 123- 141 (2016).
26. Latha, S., Raj, M.R.C., Sukumaran, R.: Use of Visualization Techniques for Active Learning
Engagement in Environmental Science Engineering Courses. International Scholarly and
Scientific Research & Innovation 10(4), 1340-1344 (2016).
27. Filva, D.A., Penalvo, F.J.G., Forment,M.A.: Social Network Analysis Approaches for Social
Learning Support.Proceedings of the Second International Conference on Technological
Ecosystems for Enhancing Multiculturality, Spain, 269-274(2014).
28. Perovic,D.: Data Mining Influence On E-Learning. The Sixth International Conference on
e-Learning,Serbia,Belgrade (2015).
29. Butts,C.T.: Social Network Analysis: A Methodological Introduction. Asian Journal of So-
cial Psychology 11, 13-41 (2008).
30. Khalil, M., Wong, J., de Koning, B. B., Ebner, M., Paas, F.: Gamification in MOOCs: A
Review of the State of the Art, IEEE Global Engineering Education Conference, 1635-1644
(2018).
31. Glover, I.: Play As You Learn: Gamification as a Technique for Motivating Learners, Shef-
field Hallam University Research Archive, http://orcid.org/0000-0002-1078-5281 ,last ac-
cessed 2019/04/22.
32. Brull, S., Finlayson, S.: Importance of Gamification in Increasing Learning,.The Journal of
Continuing Education in Nursing 47(8),372-375 (2016).
33. Dicheva, D., Dichev, C., Agre, G.,Angelova, G.: Gamification In Education: A Systematic
Mapping Study. Educational Technology & Society 18(3),75-88 (2015).
34. Khail, M., Traghi, B., ,Ebner, M. :Engaging Learning Analytics In MOOCS: The Good, The
Bad, And The Ugly. International Conference On Education and New Developments (2016).
35. Chang, G., Healey, M., McHugh, J.A.M., Wang, T.L. :Mining the World Wide Web An
Information Search Approach,Kluwer Academic Publisher, Boston (2001).
36. Sundari, J.G.,Sundae, D.: A Study of Various Text Mining Techniques. International Journal
of Advanced Networking & Applications (IJANA) 8(5), 82-85 (2017).
37. Pardos, Z.A.,Horodyskyj ,L.: Analysis of Student Behaviour in Habitable Worlds Using
Continuous Representation Visualization,.The Journal of Learning Analytics 6(1), 1-15
(2019).
38. Müller, T.:Social Network Analysis: A Practical Method To Improve Knowledge Sharing,
Hands-On Knowledge Co-Creation And Sharing; Practival Methods And Techniques,
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=1467609 , last accessed 2019/04/25.
14
39. Morschheuser, B., Hassan, L.,Werder, K., Hamari, J.: How To Design Gamification? A
Method for Engineering Gamified Software, Information and Software Technology 95, 219-
237 (2018).
40. Chea,C.: Benefits And Challenges Of Massive Open Online Courses. ASEAN Journal of
Open Distance Learning 8(1),16-23 (2016).
41. Manderveld,J.: Grand Challenges For Learning Analytics And Open & Online Education.
Open and Online Education, 70-74 (2015).
42. Avella, J.T., Kebrithchi, M., Nunn,S.G., Knai, T.: Learning Analytics Methods, Benefits,
and Challenges in Higher Education: A Systematic Literature Review. Online Learning
20(2) (2016).
43. Ebner,M., Pronegg,M.: Use of Learning Analytics Applications in Mathematics with Ele-
mentary Learners. International Journal of Academic Research in Education 1(2), 26-39
(2015).
44. Mukala, P., Buijs, J. C. A. M.,Van Der Aalst, W. M. P.: Exploring Students’ Learning Be-
haviour In Moocs Using Process Mining Techniques, Department of Mathematics and Com-
puter Science, University of Technology, Eindhoven, The Netherlands, 179-196 (2015).
45. Tucker, C., Pursel, B.K .: Mining Student-Generated Textual Data In Moocs And Quantify-
ing Their Effects On Student Performance And Learning Outcomes,.The ASEE Computers
in Education (CoED) Journal 4(5), 84 (2014).
46. Zhang, T., Yuan, B.: Visualizing MOOC User Behaviors: A Case Study on XuetangX. In
International Conference on Intelligent Data Engineering and Automated Learning,
Springer, Cham, 89-98 (2016)
47. Kellogg, S., Booth, S., Oliver, K.: A Social Network Perspective On Peer Supported Learn-
ing in MOOCs for Educators. The International Review of Research in Open and Distributed
Learning 15(5) (2014).
48. Vaibhav, A., Gupta, P.: Gamification of Moocs for Increasing User Engagement. In 2014
IEEE International Conference on MOOC, Innovation and Technology in Education
(MITE), 290-295(2014).
49. Ferguson, R.: Learning Analytics: Drivers, Developments and Challenges. International
Journal of Technology Enhanced Learning, 4(5/6), 304317 (2012).
... EDM is considered as a methodology for mining regularities from big educational data that are gathered in educational environments [2]. LA is aimed at tools development for analyzing and optimization learning [3,4]. ...
Conference Paper
Full-text available
The perspectives of application of machine learning, especially, decision trees, random forest and deep learning for educational data mining problem solving, and learning analytics tools development are considered in the paper. The abilities of sentiment analysis with BERT deep model, clustering based on kMeans with the different approaches to the text vectorization are investigated for the development of learning analytics tools on the example of the learning analytics of some programming MOOCs from Udemy. We analyze 300 titles of MOOCs and proposed their clustering for better understanding the directions of learning and skills, and 1150 sentences that contain the word «teacher» or its synonyms and 2365 sentences about the course for sentiments detection of students and top of words that describe opinions with positive and negative polarities and the issues during learning.
Article
Full-text available
Massive Open Online Courses (MOOCs) remarkably attracted global media attention, but the spotlight has been concentrated on a handful of English-language providers. While Coursera, edX, Udacity, and FutureLearn received most of the attention and scrutiny, an entirely new ecosystem of local MOOC providers was growing in parallel. This ecosystem is harder to study than the major players: they are spread around the world, have less staff devoted to maintaining research data, and operate in multiple languages with university and corporate regional partners. To better understand how online learning opportunities are expanding through this regional MOOC ecosystem, we created a research partnership among 15 different MOOC providers from nine countries. We gathered data from over eight million learners in six thousand MOOCs, and we conducted a large-scale survey with more than 10 thousand participants. From our analysis, we argue that these regional providers may be better positioned to meet the goals of expanding access to higher education in their regions than the better-known global providers. To make this claim we highlight three trends: first, regional providers attract a larger local population with more inclusive demographic profiles; second, students predominantly choose their courses based on topical interest, and regional providers do a better job at catering to those needs; and third, many students feel more at ease learning from institutions they already know and have references from. Our work raises the importance of local education in the global MOOC ecosystem, while calling for additional research and conversations across the diversity of MOOC providers.
Conference Paper
Full-text available
Learning Analytics (LA) studies the learning process in order to optimize learning opportunities for students. Although LA has quickly risen to prominence, there remain questions regarding the impact LA has made to date. To evaluate the extent that LA has impacted our understanding of learning and produced insights that have been translated to mainstream practice or contributed to theory, we reviewed the research published in 2011-2018 LAK conferences and Journal of Learning Analytics. The reviewed studies were coded according to five dimensions: study focus, data types, purpose, institutional setting, and scale of research and implementation. The coding and subsequent epistemic network analysis indicates that while LA research has developed in the areas of focus and sophistication of analyses, the impact on practice, theory and frameworks have been limited. We hypothesize that this finding is due to a continuing predominance of small-scale techno-centric exploratory studies that to date have not fully accounted for the multi-disciplinarity that comprises education. For the field to reach its potential in understanding and optimizing learning and learning environments, there must be a purposeful shift to move from exploratory models to more holistic and integrative systems-level research. This necessitates greater effort applied to understanding the research cycles that emerge when multiple knowledge domains coalesce into new fields of research.
Article
Full-text available
Massive Open Online Courses (MOOCs) have been experiencing increasing use and popularity in highly ranked universities in recent years. The opportunity of accessing high quality courseware content within such platforms, while eliminating the burden of educational, financial and geographical obstacles has led to a rapid growth in participant numbers. The increasing number and diversity of participating learners has opened up new horizons to the research community for the investigation of effective learning environments. Learning Analytics has been used to investigate the impact of engagement on student performance. However, extensive literature review indicates that there is little research on the impact of MOOCs, particularly in analyzing the link between behavioral engagement and motivation as predictors of learning outcomes. In this study, we consider a dataset, which originates from online courses provided by Harvard University and Massachusetts Institute of Technology, delivered through the edX platform [1]. Two sets of empirical experiments are conducted using both statistical and machine learning techniques. Statistical methods are used to examine the association between engagement level and performance, including the consideration of learner educational backgrounds. The results indicate a significant gap between success and failure outcome learner groups, where successful learners are found to read and watch course material to a higher degree. Machine learning algorithms are used to automatically detect learners who are lacking in motivation at an early time in the course, thus providing instructors with insight in regards to student withdrawal.
Conference Paper
Full-text available
A Massive Open Online Course (MOOC) is a type of online learning environment that has the potential to increase students' access to education. However, the low completion rates in MOOCs suggest that student engagement and progression in the courses are problematic. Following the increasing adoption of gamification in education, it is possible that gamification can also be effectively adopted in MOOCs to enhance students' motivation and increase completion rates. Yet at present, the extent to which gamification has been examined in MOOCs is not known. Considering the myriad gamification elements that can be adopted in MOOCs (e.g., leaderboards and digital badges), this theoretical research study reviews scholarly publications examining gamification of MOOCs. The main purpose is to provide an overview of studies on gamification in MOOCs, types of research studies, theories applied, gamification elements implemented, methods of implementation, the overall impact of gamification in MOOCs, and the challenges faced by researchers and practitioners when implementing gamification in MOOCs. The results of the literature study indicate that research on gamification in MOOCs is in its early stages. While there are only a handful of empirical research studies, results of the experiments generally showed a positive relation between gamification and student motivation and engagement. It is concluded that there is a need for further studies using educational theories to account for the effects of employing gamification in MOOCs.
Article
Full-text available
The number of publications in the field of medical education is still markedly low, despite recognition of the value of the discipline in the medical education literature, and exponential growth of publications in other fields. This necessitates raising awareness of the research methods and potential benefits of learning analytics (LA). The aim of this paper was to offer a methodological systemic review of empirical LA research in the field of medical education and a general overview of the common methods used in the field in general. Search was done in Medline database using the term "LA." Inclusion criteria included empirical original research articles investigating LA using qualitative, quantitative, or mixed methodologies. Articles were also required to be written in English, published in a scholarly peer-reviewed journal and have a dedicated section for methods and results. A Medline search resulted in only six articles fulfilling the inclusion criteria for this review. Most of the studies collected data about learners from learning management systems or online learning resources. Analysis used mostly quantitative methods including descriptive statistics, correlation tests, and regression models in two studies. Patterns of online behavior and usage of the digital resources as well as predicting achievement was the outcome most studies investigated. Research about LA in the field of medical education is still in infancy, with more questions than answers. The early studies are encouraging and showed that patterns of online learning can be easily revealed as well as predicting students' performance.
Article
Full-text available
Educational technology has obtained great importance over the last fifteen years. At present, the umbrella of educational technology incorporates multitudes of engaging online environments and fields. Learning analytics and Massive Open Online Courses (MOOCs) are two of the most relevant emerging topics in this domain. Since they are open to everyone at no cost, MOOCs excel in attracting numerous participants that can reach hundreds and hundreds of thousands. Experts from different disciplines have shown significant interest in MOOCs as the phenomenon has rapidly grown. In fact, MOOCs have been proven to scale education in disparate areas. Their benefits are crystallized in the improvement of educational outcomes, reduction of costs and accessibility expansion. Due to their unusual massiveness, the large datasets of MOOC platforms require advanced tools and methodologies for further examination. The key importance of learning analytics is reflected here. MOOCs offer diverse challenges and practices for learning analytics to tackle. In view of that, this thesis combines both fields in order to investigate further steps in the learning analytics capabilities in MOOCs. The primary research of this dissertation focuses on the integration of learning analytics in MOOCs, and thereafter looks into examining students' behavior on one side and bridging MOOC issues on the other side. The research was done on the Austrian iMooX xMOOC platform. We followed the prototyping and case studies research methodology to carry out the research questions of this dissertation. The main contributions incorporate designing a general learning analytics framework, learning analytics prototype, records of students' behavior in nearly every MOOC's variables (discussion forums, interactions in videos, self-assessment quizzes, login frequency), a cluster of student engagement...
Article
Full-text available
Article
Full-text available
We introduce a novel approach to visualizing temporal clickstream behaviour in the context of a degree-satisfying online course, Habitable Worlds, offered through Arizona State University. The current practice for visualizing behaviour within a digital learning environment has been to utilize state space graphs and other plots of descriptive statistics on resource transitions. While these forms can be visually engaging, they rely on conditional frequency tabulations which lack contextual depth and require assumptions about the patterns being sought. Skip-grams and other representation learning techniques position elements into a vector space which can capture a wide scope of regularities in the data. These regularities can then be projected onto a two-dimensional perceptual space using dimensionality reduction techniques designed to retain relationships information encoded in the learned representations. While these visualization techniques have been used before in the broader machine learning community to better understand the makeup of a neural network hidden layer or the relationship between word vectors, we apply them to online behavioral learner data and go a step further; exploring the impact of the parameters of the model on producing tangible, non-trivial observations of behaviour that are illuminating and suggestive of pedagogical improvement to the course designers and instructors. The methodology introduced in this paper led to an improved understanding of passing and non-passing student behavior in the course and is widely applicable to other datasets of clickstream activity where investigators and stakeholders wish to organically surface principal behavioral patterns.
Article
Full-text available
Since its inception around 2010, gamification has become one of the top technology and software trends. However, gamification has also been regarded as one of the most challenging areas of software engineering. Beyond traditional software design requirements, designing gamification requires the command of disciplines such as (motivational/behavioral) psychology, game design, and narratology, making the development of gamified software a challenge for traditional software developers. Gamification software inhabits a finely tuned niche of software engineering that seeks for both high functionality and engagement; beyond technical flawlessness, gamification has to motivate and affect users. Consequently, it has also been projected that most gamified software is doomed to fail. This paper seeks to advance the understanding of designing gamification and to provide a comprehensive method for developing gamified software. We approach the research problem via a design science research approach; firstly, by synthesizing the current body of literature on gamification design methods and by interviewing 25 gamification experts, producing a comprehensive list of design principles for developing gamified software. Secondly, and more importantly, we develop a detailed method for engineering of gamified software based on the gathered knowledge and design principles. Finally, we conduct an evaluation of the artifacts via interviews of ten gamification experts and implementation of the engineering method in a gamification project. As results of the study, we present the method and key design principles for engineering gamified software. Based on the empirical and expert evaluation, the developed method was deemed as comprehensive, implementable, complete, and useful. We deliver a comprehensive overview of gamification guidelines and shed novel insights into the nature of gamification development and design discourse. This paper takes first steps towards a comprehensive method for gamified software engineering.
Article
Recently, interest in how this data can be used to improve teaching and learning has also seen unprecedented growth and the emergence of the field of learning analytics. In other fields, analytics tools already enable the statistical evaluation of rich data sources and the identification of patterns within the data. These patterns are then used to better predict future events and make informed decisions aimed at improving outcomes (Educause, 2010). This paper reviews the literature related to this emerging field and seeks to define learning analytics, its processes, and its potential to advance teaching and learning in online education.
Chapter
The target of KDD CUP 2015 is to use the MOOC (Massive Open Online Course) user dataset provided by XuetangX to predict whether a user will drop a course. However, despite of the encouraging performance achieved, the dataset itself is largely not well investigated. To gain an in-depth understanding of MOOC user behaviors, we conduct two case studies on the dataset containing the information of 79,186 users and 39 courses. In the first case study, we use visualization techniques to show that some courses are more likely to be simultaneously enrolled than others. Furthermore, a set of association rules among courses are discovered using the Apriori algorithm, confirming the practicability of using historical enrollment data to recommend courses for users. Meanwhile, clustering analysis reveals the existence of clear grouping patterns. In the second case study, we examine the influence of two user factors on the dropout rate using visualization, providing valuable guidance for maintaining student learning activities.