learning analytics: trends and issues of the empirical research of the years 2011-2014
TRANSCRIPT
Learning Analytics: Trends and Issues of the Empirical Research of the Years 2011-2014
Nic. Nistor, Michael Derntl, & Ralf Klamma
EC-TEL 2015 Toledo, Spain
1. Introduction
Tasks and methods of Learning Analytics (LA) (Baker & Siemens, 2015) • predicting learning behaviour and output • structure discovery: clustering (learner types), social network analysis • relationship mining • distillation of data for human judgement: monitoring, visualizing • discovery with models • tool development for LA
Ø Open issue…
Nistor, Derntl, & Klamma, EC-TEL2015
2. Purpose
Overview of the empirical LA research 2011-2014 • educational setting • data sources • theoretical framework
from educational perspective • purpose of data processing • associated computational methods
Nistor, Derntl, & Klamma, EC-TEL2015
3. Methodology
Methodology • Analysed body of literature: 480 conference papers
– 298 papers from EC-TEL 2011-2014 – 182 papers from LAK 2011-2014
• 197 papers (71 EC-TEL, 126 LAK) were considered relevant
Nistor, Derntl, & Klamma, EC-TEL2015
3. Methodology
Methodology • dynamic topic model using the topic modelling toolkit D-
VITA (http://monet.informatik.rwth-aachen.de/DVita?id=3001)
• Final manual analysis of 19 most central papers (12 LAK 2014, 7 EC-TEL 2014)
Nistor, Derntl, & Klamma, EC-TEL2015
4. Findings
Educational setting • University/college: 12 cases, [8–10, 12, 13, 15,
17–19, 21, 23, 25] • School: 6 cases, [11, 14, 16, 20, 22, 24] • Informal Settings: Total: 1 case, [26]
Nistor, Derntl, & Klamma, EC-TEL2015
4. Findings
Data sources – from isolated (scalable) cases to Big Data • Learning management system log data: 11
cases, [8, 9, 11, 13, 14, 18–20, 23–25] • Learner-generated data: 4 cases, [10, 12, 21, 26] • Additionally collected data: 3 cases, [16, 17, 22] • Available academic administration data: 1 case,
[15]
Nistor, Derntl, & Klamma, EC-TEL2015
4. Findings
Theoretical framework from educational perspective • No Specific Educational Theoretical Framework
Acknowledged: 7 cases, [8, 13, 15, 18, 23–25] • Linguistic/Logic Approach: 3 cases, [10, 21, 26] • Situated Learning/Community of Practice: 2 cases, [9, 16] • Vygotsky’s Zone of Proximal Development: 2 cases, [14, 22] • Various Approaches: self-regulated learning [12], adaptive
learning environments [11], peer assessment [19], autism [20], or the instructional design concept of learning orchestration [17]
Nistor, Derntl, & Klamma, EC-TEL2015
4. Findings
Purpose of data processing • Learning Trajectory Visualization: 7 cases, [9, 10,
12, 13, 21, 23, 25] • Predicting Learning Success or Failure/Dropout: 5
cases, [8, 14, 15, 18, 22] • Diagnosis: 3 cases, [17, 20, 24] • Assessment: 2 cases, [16, 19] • Intervention (e.g., automatically adapting or
recommending learning material): 2 cases, [11, 26]
Nistor, Derntl, & Klamma, EC-TEL2015
4. Findings
Associated computational methods • Prediction: 7 cases [10, 15, 16, 18, 21, 22, 24] • Structure Discovery: 3 cases, clustering [8, 26]
and social network analysis [13] • Relationship Mining: 6 cases, correlation mining
[12, 17, 19], association rule mining [11] and others with mixed approaches [20, 25]
• Visualization: 3 cases, [9, 14, 23]
Nistor, Derntl, & Klamma, EC-TEL2015
6. Discussion
Summary of findings • Mainstream:
– examine log data to visualize learning trajectories and predict the success or failure of university students
• Innovative studies: – informal learning in online communities – video/audio records – automated student learning assessment – error/misconception diagnosis
Nistor, Derntl, & Klamma, EC-TEL2015
7. Consequences
Recommendation • Educational and psychological theories urgently
needed for in-depth understanding of educational phenomena, and for significant progress of upcoming LA research
Nistor, Derntl, & Klamma, EC-TEL2015
Thank you for your attention! [email protected]
Nistor, Derntl, & Klamma, EC-TEL2015
References
LAK 2014 Papers • 6. Pistilli MD, Willis J, Koch D et al. (eds) (2014) Proceedings of Learning Analytics and Knowledge
Conference 2014, LAK ’14. ACM, New York • 8. Bogarín A, Romero C, Cerezo R et al. (2014) Clustering for improving educational process mining. In [6],
pp 11–15 • 9. Clow D (2014) Data wranglers: human interpreters to help close the feedback loop. In [6], pp 49–53 • 10. Coopey E, Shapiro RB, Danahy E (2014) Collaborative spatial classification. In [6], pp 138–142 • 11. Fancsali SE, Ritter S (2014) Context personalization, preferences, and performance in an intelligent tutoring
system for middle school mathematics. In [6], pp 73–77 • 12. Gasevic D, Mirriahi N, Dawson S (2014) Analytics of the effects of video use and instruction to support
reflective learning. In [6], pp 123–132 • 13. Hecking T, Ziebarth S, Hoppe HU (2014) Analysis of dynamic resource access patterns in a blended
learning course. In [6], pp 173–182 • 14. Mendiburo M, Sulcer B, Hasselbring TS (2014) Interaction design for improved analytics. In [6], pp 78–82 • 15. Nam S, Lonn S, Brown T et al. (2014) Customized course advising: investigating engineering student
success with incoming profiles and patterns of concurrent course enrollment. In [6], pp 16–25 • 16. Okada M, Tada M (2014) Formative assessment method of real-world learning by integrating
heterogeneous elements of behavior, knowledge, and the environment. In [6], pp 1–10 • 17. Raca M, Tormey R, Dillenbourg P (2014) Sleepers' lag - study on motion and attention. In [6], pp 36–43 • 18. Santos JL, Klerkx J, Duval E et al. (2014) Success, activity and drop-outs in MOOCs an exploratory study
on the UNED COMA courses. In [6], pp 98–102 • 19. Vozniuk A, Holzer A, Gillet D (2014) Peer assessment based on ratings in a social media course. In [6],
pp 133–137 Nistor, Derntl, & Klamma, EC-TEL2015
References
EC-TEL 2014 Papers • 7. Rensing C, Freitas S de, Ley T et al. (eds) (2014) Open Learning and Teaching in Educational
Communities: 9th European Conference on Technology Enhanced Learning, EC-TEL 2014, Graz, Austria, September 16-19, 2014, Proceedings. Lecture Notes in Computer Science, vol 8719. Springer, Berlin
• 20. Cabielles-Hernández D, Pérez Pérez JR, Paule-Ruiz MP et al. (2014) dmTEA: Mobile Learning to Aid in the Diagnosis of Autism Spectrum Disorders. In [7], pp 29–41
• 21. González López S, López-López A (2014) Analysis of Concept Sequencing in Student Drafts. In [7], pp 422–427
• 22. Janning R, Schatten C, Schmidt-Thieme L (2014) Feature Analysis for Affect Recognition Supporting Task Sequencing in Adaptive Intelligent Tutoring Systems. In [7], pp 179–192
• 23. Loboda TD, Guerra J, Hosseini R et al. (2014) Mastery Grids: An Open Source Social Educational Progress Visualization. In [7], pp 235–248
• 24. McTavish TS, Larusson JA (2014) Labeling Mathematical Errors to Reveal Cognitive States. In [7], pp 446–451
• 25. Vahdat M, Oneto L, Ghio A et al. (2014) A Learning Analytics Methodology to Profile Students Behavior and Explore Interactions with a Digital Electronics Simulator. In [7], pp 596–597
• 26. Niemann K, Wolpers M (2014) Usage-Based Clustering of Learning Resources to Improve Recommendations. In [7], pp 317–330
Nistor, Derntl, & Klamma, EC-TEL2015