In technology-enhanced learning, activity-based learner models can provide evidence for competence assessment. Such models are the foundation for learning and teaching support, such as: adaptation, assessment, and competence analytics, recommendations, and so on. This paper analyses how to construct activity-based learner models based on existing data in the Moodle learning management system. Based on the activity theory model and the actuator-indicator model, aggregators of learner activities for different activity types were implemented in Moodle. This requires the consideration of the social roles in a course, in order to enable adaptive views for learners and instructors on the stored activity information. The implementation showed that Moodle stores information about course activities that requires filtering before it can get used for higher level processing. The social planes in Moodle reveal a higher complexity than it has been previously described by theories of classroom orchestration, such as actors who are no longer present in a course.
Testing tools and AI - ideas what to try with some tool examples
Activity-Based Learner-Models for Learner Monitoring and Recommendations in Moodle
1. Beatriz Florian Christian Glahn Hendrik Drachsler Marcus Specht Ramón Fabregat
Presented at EC-TEL 2011
Sixth European Conference on Technology Enhanced Learning
Towards Ubiquitous Learning
Palermo (Italy), 22 September 2011
0
2. Beatriz Florian, Christian Glahn, Hendrik Drachsler, Marcus Specht, Ramón Fabregat
Institute of Informatics and Applications (IIiA),
University of Girona, Girona, Spain
Centre for Learning Science
Open University of The Netherlands
Escuela de Ingeniería de Sistemas y Computación
Universidad del Valle. Cali, Colombia 1
3. Motivation
Research Question
Background
Competence Assessment
Activity Theory
Actuator-Indicator Model
Architecture
Activity-Based Learner-Models
Learning Analytics Solutions
Prototype and Findings
Conclusions and On-going Research
EC-TEL 2011 Activity-Based Learner-Models for Learner Monitoring and Recommendations in Moodle 2
4. Motivation
Research Q Background Architecture Prototype Conclusions
❶ ② ③ ④ ⑤
Appropriate
Activity
support
traces
responses
EC-TEL 2011 Activity-Based Learner-Models for Learner Monitoring and Recommendations in Moodle 3
5. Motivation
Research Q. Background Architecture Prototype Conclusions
❶ ❷ ③ ④ ⑤
Appropriate
Activity traces support
responses
EC-TEL 2011 Activity-Based Learner-Models for Learner Monitoring and Recommendations in Moodle 4
6. Motivation
Research Q. Background Architecture Prototype Conclusions
❶ ❷ ❸ ④ ⑤
EC-TEL 2011 Activity-Based Learner-Models for Learner Monitoring and Recommendations in Moodle 5
7. Motivation
Research Q. Background Architecture Prototype Conclusions
❶ ❷ ❸ ❹ ⑤
Activity-based learner-models in
• What ?
• Where?
• How?
• When?
EC-TEL 2011 Activity-Based Learner-Models for Learner Monitoring and Recommendations in Moodle 6
8. Motivation
Research Q. Background Architecture Prototype Conclusions
❶ ❷ ❸ ❹ ❺
complex to extract semantic meaning
limited built-in support for learning analytics
Workshop
Quiz Others
Lesson
Assessment in Moodle is more focus on summative assessment
EC-TEL 2011 Activity-Based Learner-Models for Learner Monitoring and Recommendations in Moodle 7
9. Motivation Research Q
Background Architecture Prototype Conclusions
❶ ❷ ❸ ❹ ❺ ❶.
EC-TEL 2011 Activity-Based Learner-Models for Learner Monitoring and Recommendations in Moodle 8
10. Motivation Research Q Background
Architecture Prototype Conclusions
❶ ❷ ❸ ❹ ❺ ❶. ❶ ② ③ ④ ⑤
2005 2009 2010
Cheetham, G. & Florian, B., Commission Crespo, R. M.,
Chivers, G. Baldiris, S., of the Najjar, J., Derntl,
Fabregat R. European M., Leony, D.,
Communities Neumann, S.,
Oberhuemer, P.,
et al.
Najjar J. et al. Florian, B., De La
Hoz, A., Baldiris,
S., Fabregat R.
9
12. Motivation Research Q Background
Architecture Prototype Conclusions
❶ ❷ ❸ ❹ ❺ ❶. ❶ ❷ ❸ ④ ⑤
EC-TEL 2011 Activity-Based Learner-Models for Learner Monitoring and Recommendations in Moodle 11
13. Motivation Research Q Background
Architecture Prototype Conclusions
❶ ❷ ❸ ❹ ❺ ❶. ❶ ❷ ❸ ❹ ⑤
2005 2007 2008 2009 2010
Zimmermann, A., Glahn, C., De Jong, T., Glahn, C., Glahn, C., &
Specht, M., Loren Specht, M., Specht, M., Specht, M., Specht, M.
z, A. & Koper, R. & Koper, R. & Koper, R.
Glahn, C.,
Specht, M.,
& Koper, R.
12
14. Motivation Research Q Background
Architecture Prototype Conclusions
❶ ❷ ❸ ❹ ❺ ❶. ❶ ❷ ❸ ❹ ❺
EC-TEL 2011 Activity-Based Learner-Models for Learner Monitoring and Recommendations in Moodle 13
15. Motivation Research Q Background Architecture
Prototype Conclusions
❶ ❷ ❸ ❹ ❺ ❶. ❶ ❷ ❸ ❹ ❺ ❶ ②
EC-TEL 2011 Activity-Based Learner-Models for Learner Monitoring and Recommendations in Moodle 14
16. Motivation Research Q Background Architecture
Prototype Conclusions
❶ ❷ ❸ ❹ ❺ ❶. ❶ ❷ ❸ ❹ ❺ ❶ ❷
EC-TEL 2011 Activity-Based Learner-Models for Learner Monitoring and Recommendations in Moodle 15
17. SE NSOR LAYER
Moodle implements a detailed activity
logging in its services
Logs in Moodle are created by the Moodle
Log Function and stored in mdl_log
Moodle database
Report logs and the report statistics.
Novel Ideas
[17]mirroring of personal tracked data to the user
[20] conceptual system-architecture for device
adaption for mobile learning
EC-TEL 2011 Activity-Based Learner-Models for Learner Monitoring and Recommendations in Moodle 16
18. SE MANTI C LAYER
Several aggregators can be active to
process the traces of learning activity
Aggregation • SQL Queries
rule
• Self
Context (Social • Peer
Planes) • Class
Role-based
• Teacher -> Class, peer, self
perspective • Student -> self, peer
(Capabilities)
EC-TEL 2011 Activity-Based Learner-Models for Learner Monitoring and Recommendations in Moodle 17
19. SE MANTI C LAYER
Other Semantic Information
Competence model (EQF)
Assessment plan
EC-TEL 2011 Activity-Based Learner-Models for Learner Monitoring and Recommendations in Moodle 18
20. CONT R OL LAYER
Plug-in that provides several
widgets that can be independently
integrated into the UI.
Each widget contains a set of
aggregators and visualizations
Scope -> social planes
In the case of recommendations an
aggregator implements the data
mining algorithms.
EC-TEL 2011 Activity-Based Learner-Models for Learner Monitoring and Recommendations in Moodle 19
21. IN DICATOR LAY ER
Different presentation modes for
the data of the control layer.
Configuration of the indicator ->
presentation mode
So far shows smart indicators
(context, the tracked activity)
Embedded into the UI of Moodle
through a JavaScript.
EC-TEL 2011 Activity-Based Learner-Models for Learner Monitoring and Recommendations in Moodle 20
22. Motivation Research Q Background Architecture Prototype
Conclusions
❶ ❷ ❸ ❹ ❺ ❶. ❶ ❷ ❸ ❹ ❺ ❶ ❷ ❶ ② ③
EC-TEL 2011 Activity-Based Learner-Models for Learner Monitoring and Recommendations in Moodle 21
23. Motivation Research Q Background Architecture Prototype
Conclusions
❶ ❷ ❸ ❹ ❺ ❶. ❶ ❷ ❸ ❹ ❺ ❶ ❷ ❶ ❷ ③
22 students no teaching staff as participant
7 unexpected
15 students 7 Former participants
students
“drop-outs” or “alumni”?
enrolled Who are they?
EC-TEL 2011 Activity-Based Learner-Models for Learner Monitoring and Recommendations in Moodle 22
24. Motivation Research Q Background Architecture Prototype Conclusions
Conclusions
❶ ❷ ❸ ❹ ❺ ❶. ❶ ❷ ❸ ❹ ❺ ❶ ❷ ❶ ❷ ❸ ❶ ②
Social Planes in the Moodle logs are complex
Greater than predicted in the literature
New perspectives on classroom orchestration
Application of learning analytics
EC-TEL 2011 Activity-Based Learner-Models for Learner Monitoring and Recommendations in Moodle 23
25. Motivation Research Q Background Architecture Prototype Conclusions
❶ ❷ ❸ ❹ ❺ ❶. ❶ ❷ ❸ ❹ ❺ ❶ ❷ ❶ ❷ ❸ ❶ ②
On-going research:
Learner Analytics based on Competences’
assessment (bflorian)
Dyslexia Diagnosis and Treatment (cmejia,
bflorian)
Indicators to help gauge whether or not a
certain competence was successfully attained
Drop-out detection system for teachers
EC-TEL 2011 Activity-Based Learner-Models for Learner Monitoring and Recommendations in Moodle 24
26. Motivation Research Q Background Architecture Prototype Conclusions
❶ ❷ ❸ ❹ ❺ ❶. ❶ ❷ ❸ ❹ ❺ ❶ ❷ ❶ ❷ ❸ ❶ ❷
Perspective in activity-based learner models as
semantically models for activity-centered
assessment and recommendations
Prototype that implements indicators as
examples of learning analytic applications
Discussion of possible benefits of the approach in
assessment, competence development and
recommender systems
EC-TEL 2011 Activity-Based Learner-Models for Learner Monitoring and Recommendations in Moodle 25
27. Motivation Research Q Background Architecture Prototype Conclusions
❶ ❷ ❸ ❹ ❺ ❶. ❶ ❷ ❸ ❹ ❺ ❶ ❷ ❶ ❷ ❸ ❶ ❷
For more information please contact
Beatriz Florián bflorian@eia.udg.edu,
beatriz.florian@correounivalle.edu.co
Christian Glahn christian.glahn@ou.nl
Hendrik Drachsler hendrik.drachsler@ou.nl
Marcus Specht marcus.specht@ou.nl
Ramón Fabregat ramon.fabregat@udg.edu
Institut d’Informàtica i Aplicacions (IIiA)
Universitat de Girona. Girona, España
Centre for Learning Science
Open University off The Netherlands
Escuela de Ingeniería de Sistemas y Computación
Universidad del Valle. Cali, Colombia 26
Editor's Notes
Good afternoon. I am Beatriz Florian, Ph.D Student of the University of Girona Spain, and I am here to present the paper ….. The otherauthors of this work, whose names you can see in this slide are: ....
EQF competence in action
Activity theory proposed by EngestromUsed in learning by Dillenbourg & Tochounikine
Proposed by Zimmerman et al and used in many different contexts.