1. LEARNING ANALYTICS AND MOOCS
Ebru İnan and Martin Ebner
Educational Technology, Graz University of Technology, Graz, Austria
einan@student.tugraz.at, martin.ebner@tugraz.at
2. Outlines
§ 1. Introduction
• Aim of Study
• Learning Analytics
• MOOCs
§ 2. Research Method
§ 3. Results of the Literature Rewiew
§ Data Categories
§ Typcal Examples
§ Advantages and Challenges
§ 4. Discussions/Conclusions
3. 1. Introduction
v Educational technologies in the 21st century
v Technology –Enhanced Learning
v Learning Analytics
v MOOCs
4. Purpose
Ø«It is aimed to present an overview of
existing learning analytics concepts
and methods strongly focused in
conjunction with Massive Open
Online Courses (MOOCs)»
ØThe Methods
ØBenefits and Challegens
5. What is the Learning Analytics?
“the measurement, collection, analysis and reporting of data about learners and their
contexts, for purposes of understanding and optimizing learning and the environment
in which it occurs.”*
*1st International Conference of Learning Analytics & Knowledge, Banff, Alberta 2011
6. MOOCs (Massive Open Online Courses)
§ The term MOOCs has been first appeared in 2008
§ The first xMOOC was the course by Stanford University in 2011.
7. 2. Research Methods
§ The search string used are “Learning Analytics” and “MOOCs” and “Massive Open
Online Course” and “Learning Analytics - MOOCs”.
§ Search queries were conducted in selected databases between 2009-2019 dates.
§ As a result, as a part of this review, it was referenced a total of 50 articles.
8. Database Last 10 Years Publication Numbers Keywords
TUBibliothek
7 Learning Analytics
6 MOOCs
2 Massive Open Online Course
2 Learning Analytics-MOOCs
Semantic Scholar
647.937 Learning Analytics
29.204 MOOCs
131.640 Massive Open Online Course
7.146 Learning Analytics-MOOCs
Web Of Science 6.300 Learning Analytics
2.714 MOOCs
2.447 Massive Open Online Course
202 Learning Analytics-MOOCs
Scopus 10.113 Learning Analytics
3.467 MOOCs
3.028 Massive Open Online Course
356 Learning Analytics-MOOCs
Google Scholar 450.000 Learning Analytics
31.700 MOOCs
295.000 Massive Open Online Course
12.900 Learning Analytics-MOOCs
DergiPark 4.060 Learning Analytics
45 MOOCs
43.877 Massive Open Online Course
4.123 Learning Analytics-MOOCs
10. Learning Analytics methods described by Khalil et al
Data Mining
Statistical and Mathematical
Text Mining-Semantics-
Linguistics Analysis
Visulization
Social Network Analysis
Gamification
Learning
Analytics
Methods
11. Data Categories/Typical Examples
• Explore student’s learning ways
• Supports to improve MOOCs
environments
• In the study conducted by Mukala et
al, Using the data mining technique, it
is seen that the student’s video
surveillance have a direct impact on
performance.
DataMining Predictions
Classification
Assosiation Rule
in Mining
Clustering
Fuzzy Logic
12. Data Categories/Typical Examples
• can use to observe the relationship
between participation rates and
achievements.
• Data such as online durations, number of
being active, visited pages etc.
• In the study carried out by Taraghi et al.
has been determined the easiest and most
difficult questions in different types and for
result used Markov statistical analysis
method.
Statisticaland
Mathematical
• Average
• Mean
• Standard
Deviotion
• Markov
Chain
13. Data Categories/Typical Examples
• Discussion sections on forums and blogs
• Tucker and Pursel worked on the effects
of the texts produced by the students on
the student performances and outputs.
Text Mining-Sematics-
Linguistics Analysis
• Summarization
• Categorization
• Retrievals
• Extract
• Cluster
https://pixabay.com/illustrations/text-mining-entity-extraction-1476780/
14. Data Categories/Typical Examples
• used for doing proper learning,
develop brainstorming and
creativity.
• Zhang and Yuan have worked on
video recordings in MOOCs to
explore the relationship among
courses.
Visulization
• Ming Map
• Concept Map
• Cognigative Map
• Radial Tree
• Semantic Map
• Rhizome
• Visual Metaphor
• Tree Structure
• Argument Map
• Social Map
15. Data Categories/Typical Examples
• to understand and optimize the learning
environment
• Kellogg, Booth and Oliver use this method
order to present a peer-assisted learning
approach in MOOCs.
Social Network
Analysis
Blockmodelling
and Equivalence
Analysis
Signed Graphs
and Structural
Balance Analysis
Dynimic Network
Analysis
• https://pixabay.com/illustrations/network-connections-communication-3537400/
16. Data Categories/Typical Examples
Gamification
• Visual Status
• Social Engagament
• Freedom of Choice
• Freedom to Fail
• Rapid feedback
• Progress
§ increases student motivation, learning
platform usage
§ participation in courses and makes
learning entertaining
§ Vaibhav and Gupta have done Gamified
and Non Gamified groups on MOOCs
and analyzed the differences.
17. Benefits and Challanges
Benefits:
• Determining the target course
• Improvement of the curriculum
• Student learning outcomes, behaviors
and processes
• Individualized learning
• Teacher performance improvement
• Post-educational employment.
Challenges:
• 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
18. 4. Conclusion
Learning Analytics is a new area and ever-developing concept. In addition to this, MOOCs with
the huge data sources have an important role in applying learning analysis. 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 Analysis, visualization, Social network analysis
and Gamification areas are implemented Learning Analytics in MOOCs allied with benefits and
challenges.