1 / 15

Precision and more

Precision and more. mk. Group recommendation for eduactional system. Engage users to discuss and to help each other within the system Incerase students collaboration Improve process of learning Personalize materials in order to users ’ learning styles. Learning styles.

honey
Download Presentation

Precision and more

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Precision and more mk

  2. Group recommendationforeduactionalsystem • Engageusers to discuss and to helpeachotherwithinthesystem • Incerasestudentscollaboration • Improveprocess of learning • Personalizematerials in order to users’ learning styles

  3. Learning styles • Perception – sensory vs intuitive • Input – visual vs auditory • Processing – active vs reflective • Understanding – sequential vs global

  4. Single user recommendation

  5. Single user recommendation

  6. Group recommendation

  7. Evaluation • What? How?

  8. Evaluation • Influence of learningstylesforthe single user recommendation • Influence of grouprecommendationforknowleadgeincrease • Pre/post test • Single learning • Group learning • New user scenario

  9. 1. Single learning • 6x normalrecommendation, 6x edhanced by learningstyles • 78 percent of clicksforrecommendationwithlearningstyles

  10. 2. Group learning

  11. Whatnext? • Rankingmeasures • Normalized Distance-based Performance Measure • Normalized Cumulative Discounted Gain • Coverage • Itemspace • Usersspace • Confidence • System trust in itsrecommendations

  12. Whatnext? 2 • Trust • User trust in therecommendersystem • Novelty • Serendipity • Howtheresults are surprising • Diversity • Opposite to similarity

  13. Whatnext? 3 • Utility • E.g. revenue • Risk • E.g. stock • Robustness • Fakeinformation • Privacy

  14. Whatnext? 4 • Adaptivity • E.g. news – shortvs. longterm • Scalability • Milions of items

  15. Evaluating Recommendation Systems. Guy Shani and AselaGunawardana, Microsoft

More Related