![Thank You! Dank U! Gracias! Questions, Comments, Critics… are all welcome!! Xavier Ochoa [email_address] http://www.cti.espol.edu.ec/xavier Erik Duval Erik.Duval@cs.kuleuven.be http://www.cs.kuleuven.ac.be/~erikd](https://image.slidesharecdn.com/relevance-ranking-of-learning-objects3789/85/Relevance-Ranking-of-Learning-Objects-30-320.jpg)
Relevance Ranking of Learning Objects
- 1. Relevance Ranking Metrics for Learning Objects Xavier Ochoa, ESPOL, Ecuador Erik Duval, KULeuven, Belgium
- 2. Agenda Why Relevance Ranking? What is Relevance? Relevance Ranking Metrics Do they work? What is next?
- 4. Economy of Abundance Put your LMS here!
- 5. Why Relevance Ranking? Abundance = Difficult to find most relevant
- 6. Why Relevance Ranking? Abundance = Difficult to find most relevant Solution: Do it the Google way
- 7. Why Relevance Ranking? Abundance = Difficult to find most relevant Relevance Ranking MEANINGFUL & SCALABLE
- 8. How we do it now? Manual rating: Meaningful but not Scalable Text based Ranking Algorithms: Scalable but not Meaningful
- 10. Relevance Ranking Metrics Relevance Ranking Metric B Metric A Metric C Context
- 11. Relevance Ranking Metrics Relevance Ranking Meaningful Metric B Metric A Metric C Context
- 12. Relevance Ranking Metrics Relevance Ranking Scalable Metric B Metric A Metric C Context
- 16. Do they work? Exploratory Study 10 users (8 Prof. and 2 R.A.) MIT OCW learning objects (34,640 LO) Search and Select Objects to create 10 lessons (10 different topics on CS) Web application was used
- 20. Ranking the Rankings Baseline Rank: TF-IDF similarity algorithm Re-rank according to Basic Metrics All rankings compared with manual relevance ranking Kendall Tau was used to measure similaritiy between lists
- 21. Results
- 22. Basic Topical Relevance Metric Trees
- 23. Basic Personal Relevance Metric Net.
- 24. Basic Situational Relevance Metric XML
- 27. Results Even basic metrics improve the ranking Linear Combination should be learnt Limited (and Synthetic) Study!
- 28. What is next? Implementation in ARIADNE NEXT Capture user behavior and learn from it for 3 months Natural (Real) evaluation of the metrics Develop BETTER metrics
- 29. Conclusions Meaningful and Scalable metrics are possible Cheap to implement Provide significant improvement While not optimal, they could be use as a base-line for further research
- 30. Thank You! Dank U! Gracias! Questions, Comments, Critics… are all welcome!! Xavier Ochoa [email_address] http://www.cti.espol.edu.ec/xavier Erik Duval Erik.Duval@cs.kuleuven.be http://www.cs.kuleuven.ac.be/~erikd