3. What is Learning Analytics?
• Using Student’s ‘Big Data’ to Improve
Teaching (Rafael Scapin, Dawson
College)
• ”collecting traces that learners leave
behind and using those traces to
improve learning.” (Eric Duval, Cath
Univ of Leuven)
• measurement, collection, analysis and
reporting of data about learners and
their contexts, for purposes of
understanding and optimising learning
and the environments in which it
occurs (SoLAR)
4. Learning Analytics Definitions: differences?
• Using Student’s ‘Big Data’ to Improve
Teaching (Rafael Scapin, Dawson
College)
• ”collecting traces that learners leave
behind and using those traces to
improve learning.” (Eric Duval, Cath
Univ of Leuven)
• measurement, collection, analysis and
reporting of data about learners and
their contexts, for purposes of
understanding and optimising learning
and the environments in which it
occurs (SoLAR)
5. Societies, Conferences
• Society for Learning Analytics and Research (SoLAR)
• International Educational Data Mining Society (IEDMS)
• Learning Analytics Conference (LAK)
• Educational Data Mining Conference (EDM)
7. 7
Stakeholders of LA
• Governments, Professional Bodies
• Universities, Institutions (bodies of education)
• Groups: classroom, learning groups, etc.
• Teachers, Academics, Administrators
• Students
• Researchers
micro, meso and macro levels
10. 10
Early Dropout Prediction for Programming Courses supported by Online Judges (AIED’19)
Earliest predictor of dropout in MOOCs: a longitudinal study of FutureLearn courses. (ISD 2018)
How is learning fluctuating? FutureLearn MOOCs fine-grained temporal Analysis and Feedback to Teachers (ISD’18)
Demographic Indicators Influencing Learning Activities in MOOCs: Learning Analytics of FutureLearn Courses (ISD’18)
LA Types
15. 15
Evolution of EDM and LA references in Google Scholar
Linan, Perez: http://rusc.uoc.edu/rusc/ca/index.php/rusc/article/view/v12n3-calvet-juan/2746.html
16.
17. Temporal Sentiment Analysis of Learners: Public Versus
Private Channels in a Women-in-Tech Conversion Course
J. Yu et al., "Temporal Sentiment Analysis of Learners: Public Versus Private Social
Media Communication Channels in a Women-in-Tech Conversion Course," 2020 15th
International Conference on Computer Science & Education (ICCSE), Delft,
Netherlands, 2020, pp. 182-187, doi: 10.1109/ICCSE49874.2020.9201631.
19. Alamri A., Sun Z., Cristea A.I., Senthilnathan G., Shi L., Stewart C. (2020) Is MOOC Learning Different for Dropouts? A
Visually-Driven, Multi-granularity Explanatory ML Approach. In: Kumar V., Troussas C. (eds) Intelligent Tutoring
Systems. ITS 2020. Lecture Notes in Computer Science, vol 12149. Springer, Cham. https://doi.org/10.1007/978-3-030-
49663-0_42
20. Result (Bird eye view)
2020
Figure 1: Learning pattern of dropout learners for Big Data course (bird eye view)
Figure 2: Learning pattern of completers learners for Big Data course (bird eye view)
21. Result ( Fish eye view)
2121
Figure 1: Learning pattern of completers for Shakespeare courseFigure 1: Learning pattern of completers for Shakespeare course (fish eye view)
Figure 2: Learning pattern of dropout learners for Shakespeare course (fish eye view)
22. Result ( statistical analysis)
➢ Learning paths of two groups of learners are statistical significantly different
2222
Table 2: P-values of linear and catch-up learning activities
23. Result
➢ Learners are more likely to drop out after articles and
videos
2323
Figure 3: Number of dropout/topic: a) first run b) second run
24. Result
➢ 17.1% dropout transfer among quizzes in Babies in Mind
➢ Nearly one-quarter of dropout learners lose interests after reading papers in
Big Data
2424
Figure 4: Babies in Mind (left) & Big Data (right): catch-up themes transition, dropout learners
25. 25
➢ Predict early dropout of four course based on time spend on each activity by
two machine learning models: XGBoost and Gradient Boosting.
Table 3: Early Prediction (in first ten percentages of course) of Dropout
Result (machine learning)
26. Pereira, F. D., Oliveira, E. H., Oliveira, D. B., Cristea, A. I., Carvalho, L. S., Fonseca, S. C., Toda, A., Isotani, S. (2020). Using
learning analytics in the Amazonas: Understanding students’ behaviour in introductory programming. British Journal of
Educational Technology, 51(4), 955–972. https://doi.org/10.1111/bjet.12953
Effective and Ineffective Behaviours
27. Pereira, F. D., Oliveira, E. H., Oliveira, D. B., Cristea, A. I., Carvalho, L. S., Fonseca, S. C., Toda, A., Isotani, S. (2020). Using
learning analytics in the Amazonas: Understanding students’ behaviour in introductory programming. British Journal of
Educational Technology, 51(4), 955–972. https://doi.org/10.1111/bjet.12953
Effective and Ineffective Behaviours
28. Samuel Fonseca, Filipe Dwan Pereira, Elaine H. T. Oliveira, David Fernandes, Leandro Carvalho and Alexandra
Cristea "Automatic Subject-based Contextualisation of Programming Assignment Lists" In: Proceedings of
The 13th International Conference on Educational Data Mining (EDM 2020), Anna N. Rafferty, Jacob
Whitehill, Violetta Cavalli-Sforza, and Cristobal Romero (eds.) 2020, pp. 81 - 91
How can we extract the subject matter from programming problem statements,
to automatically match programming assignment lists to non-CS courses?
29. Samuel Fonseca, Filipe Dwan Pereira, Elaine H. T. Oliveira, David Fernandes, Leandro Carvalho and Alexandra
Cristea "Automatic Subject-based Contextualisation of Programming Assignment Lists" In: Proceedings of
The 13th International Conference on Educational Data Mining (EDM 2020), Anna N. Rafferty, Jacob
Whitehill, Violetta Cavalli-Sforza, and Cristobal Romero (eds.) 2020, pp. 81 - 91
30. Samuel Fonseca, Filipe Dwan Pereira, Elaine H. T. Oliveira, David Fernandes, Leandro Carvalho and Alexandra
Cristea "Automatic Subject-based Contextualisation of Programming Assignment Lists" In: Proceedings of
The 13th International Conference on Educational Data Mining (EDM 2020), Anna N. Rafferty, Jacob
Whitehill, Violetta Cavalli-Sforza, and Cristobal Romero (eds.) 2020, pp. 81 - 91
31. Samuel Fonseca, Filipe Dwan Pereira, Elaine H. T. Oliveira,
David Fernandes, Leandro Carvalho and Alexandra Cristea
"Automatic Subject-based Contextualisation of
Programming Assignment Lists" In: Proceedings of The 13th
International Conference on Educational Data Mining (EDM
2020), Anna N. Rafferty, Jacob Whitehill, Violetta Cavalli-
Sforza, and Cristobal Romero (eds.) 2020, pp. 81 - 91
32. Alrajhi L., Alharbi K., Cristea A.I. (2020) A Multidimensional Deep Learner Model of Urgent Instructor
Intervention Need in MOOC Forum Posts. In: Kumar V., Troussas C. (eds) Intelligent Tutoring Systems. ITS
2020. Lecture Notes in Computer Science, vol 12149. Springer, Cham. https://doi.org/10.1007/978-3-030-
49663-0_27
RQ1: Is there a relationship between the various dimensions of the
learners’ posts and their need for urgent instructor intervention?
RQ2: Does using several dimensions as features in addition to textual
data increase the model’s predictive power of the need for urgent
instructor intervention, when using deep learning?
33. Alrajhi L., Alharbi K., Cristea A.I. (2020) A Multidimensional Deep Learner Model of Urgent Instructor
Intervention Need in MOOC Forum Posts. In: Kumar V., Troussas C. (eds) Intelligent Tutoring Systems. ITS
2020. Lecture Notes in Computer Science, vol 12149. Springer, Cham. https://doi.org/10.1007/978-3-030-
49663-0_27
34. Toda, Armando M., et al. “How to Gamify Learning
Systems? An Experience Report Using the Design Sprint
Method and a Taxonomy for Gamification Elements in
Education.” Journal of Educational Technology & Society,
vol. 22, no. 3, 2019,
pp. 47–60. JSTOR,
www.jstor.org/stable/26896709.
A. M. Toda et al., "A Taxonomy of Game
Elements for Gamification in Educational
Contexts: Proposal and Evaluation," 2019 IEEE
19th International Conference on Advanced
Learning Technologies (ICALT), Maceió, Brazil,
2019, pp. 84-88, doi:
10.1109/ICALT.2019.00028.
35. Palomino, P. T., Toda, A., Oliveira, W., et al.
(2019). Exploring Content Game Elements to
Support Gamification Design in Educational
Systems : Narrative and Storytelling. In
Proceedings of the SBIE 2019.
36. AI: Top Down versus Bottom Up
36
(Student) usage data
Educational
Adaptive/Personalised System
Educators, Psychologists, Teachers,
etc.
38. Concluding Remarks
• LA for Big Data is here to stay
• We shall see more interesting methods from
various areas in the future
• The world has shifted to online work, and
institutions everywhere are taking the actual
implementation side of LA more seriously
38