How Recommender Systems in Technology-Enhanced Learning depend on Context
1. How Recommender Systems in
Technology-Enhanced Learning
depend on Context
Hendrik Drachsler Nikos Manouselis
Open University of the Greek Research
Netherlands Technology Network
2. TEL context
Figure by : Cross, J. (2006). Informal learning: Rediscovering the
natural pathways that inspire innovation and performance.
San Francisco, CA: Pfeiffer.
hendrik.drachsler@ou.nl
STELLAR - Alpine rendez-vous workshop on context-aware recommendation 2009, Garmisch-Partenkirchen, DE
Page 2 | November 30, 2009
3. Formal learning
• are learning offers from
educational institutions.
• is imbedded into a curriculum or
syllabus framework.
Figure by: • is highly structured.
Cross, J. (2006) • leads to a specific accreditation.
• involves domain experts to
guarantee quality.
hendrik.drachsler@ou.nl
STELLAR - Alpine rendez-vous workshop on context-aware recommendation 2009, Garmisch-Partenkirchen, DE
Page 3 | November 30, 2009
4. Formal learning = structured
layers
Generic layers within a simplified architecture of an educational AEH
(Karampiperis & Sampson, 2005)
hendrik.drachsler@ou.nl
STELLAR - Alpine rendez-vous workshop on context-aware recommendation 2009, Garmisch-Partenkirchen, DE
Page 4 | November 30, 2009
5. Informal learning
• content is provide from different
sources.
• happens outside formal
educational settings (e.g.
Figure by: related to work or leisure time.
Cross, J. (2006) • is less structured (in terms of
learning goals, study time or
learning support).
• does not lead to a certain
hendrik.drachsler@ou.nl
accreditation.
STELLAR - Alpine rendez-vous workshop on context-aware recommendation 2009, Garmisch-Partenkirchen, DE
Page 5 | November 30, 2009
6. Informal learning = emergence
hendrik.drachsler@ou.nl
STELLAR - Alpine rendez-vous workshop on context-aware recommendation 2009, Garmisch-Partenkirchen, DE
Page 6 | November 30, 2009
7. Context variables
Formal learning
Curriculum (Closed-Corpus)
Teacher directed
Predefined learning resources, learning goals
Maintenance
Informal learning
Learning resources from different providers (Open-Corpus)
More self-directed learning goals
Responsible for own learning pace / path
Lack of maintenance
hendrik.drachsler@ou.nl
STELLAR - Alpine rendez-vous workshop on context-aware recommendation 2009, Garmisch-Partenkirchen, DE
Page 7 | November 30, 2009
8. Recommendation approaches
Learning settings, environmental conditions
and the task greatly affect the design of
recommender systems in TEL.
systems in TEL.
hendrik.drachsler@ou.nl
STELLAR - Alpine rendez-vous workshop on context-aware recommendation 2009, Garmisch-Partenkirchen, DE
Page 8 | November 30, 2009
10. Informal recommendation
approach
Hierarchical
Clustering Layer n
clustering
(bottom-up)
Clustering Layer 1..n
Content Layer
hendrik.drachsler@ou.nl
STELLAR - Alpine rendez-vous workshop on context-aware recommendation 2009, Garmisch-Partenkirchen, DE
Page 10 | November 30, 2009
11. Research question
How can we get the best out of both worlds?
hendrik.drachsler@ou.nl
STELLAR - Alpine rendez-vous workshop on context-aware recommendation 2009, Garmisch-Partenkirchen, DE
Page 11 | November 30, 2009
12. A solution for formal learning
hendrik.drachsler@ou.nl
STELLAR - Alpine rendez-vous workshop on context-aware recommendation 2009, Garmisch-Partenkirchen, DE
Page 12 | November 30, 2009
13. A solution for informal learning
• 100 user (hopefully some more after today )
• 20000 Web 2.0 items (increasing every hour)
• 700 ratings in the data base
• 10000 tags in the data base
hendrik.drachsler@ou.nl
STELLAR - Alpine rendez-vous workshop on context-aware recommendation 2009, Garmisch-Partenkirchen, DE
Page 13 | November 30, 2009
15. Version 1.0
DUINE Prediction
Engine
Database User Interface
of Items
hendrik.drachsler@ou.nl
STELLAR - Alpine rendez-vous workshop on context-aware recommendation 2009, Garmisch-Partenkirchen, DE
Page 15 | November 30, 2009
16. How does it work?
Cold-Start = Tag-based recommendation
Collaborative Filtering with ratings
hendrik.drachsler@ou.nl
STELLAR - Alpine rendez-vous workshop on context-aware recommendation 2009, Garmisch-Partenkirchen, DE
Page 16 | November 30, 2009
18. Conclusions
Fed by bottom-up
approach
How to
combine?
Fed by top-down
approach
hendrik.drachsler@ou.nl
STELLAR - Alpine rendez-vous workshop on context-aware recommendation 2009, Garmisch-Partenkirchen, DE
Page 18 | November 30, 2009
20. Many thanks for your interest!
This slide is available here:
http://www.slideshare.com/Drachsler
Email: hendrik.drachsler@ou.nl
Skype: celstec-hendrik.drachsler
Blogging at: http://elgg.ou.nl/hdr/weblog
Twittering at: http://twitter.com/HDrachsler
hendrik.drachsler@ou.nl
STELLAR - Alpine rendez-vous workshop on context-aware recommendation 2009, Garmisch-Partenkirchen, DE
Page 20 | November 30, 2009
21. You can use it as well!
Please sign up at:
Register at ReMashed
remashed.ou.nl. starts mashing.
http://remashed.ou.nl
Enter your favorite Taste your
Web 2.0 potatoes. personal
flavor of
Web 2.0.
Join the
community.
hendrik.drachsler@ou.nl
STELLAR - Alpine rendez-vous workshop on context-aware recommendation 2009, Garmisch-Partenkirchen, DE
Page 21 | November 30, 2009