Visualisatie van muziekaanbevelingen Promotor: Prof. Dr. Ir. E. Duval, Prof. Dr. K. Verbert, Dr. J. Klerkx Begeleider: Prof. Dr. K. Verbert, Dr. J. Klerkx FACULTEIT WETENSCHAPPEN Een visueel uitlegsysteem voor collaboratieve filtering Joris SCHELFAUT Academiejaar 2012- 2013
Final presentation for the thesis "visualization of music suggestions". Read the thesis text online at http://soundsuggest.wordpress.com
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Visualisatie van muziekaanbevelingen
Promotor:Prof. Dr. Ir. E. Duval, Prof. Dr. K. Verbert, Dr. J. KlerkxBegeleider:Prof. Dr. K. Verbert, Dr. J. Klerkx
FACULTEIT WETENSCHAPPEN
Een visueel uitlegsysteem voor collaboratieve filtering
Joris SCHELFAUT
Academiejaar 2012-2013
Recommender system
FACULTEIT WETENSCHAPPEN
• Compute personalized item suggestions based on the user’s interaction with the system– Listening history– Items ratings– Item purchases– …
• Last.fm, Netflix, IMDb, Facebook, Amazon, …
Recommender system
FACULTEIT WETENSCHAPPEN
• Database (items / users)
Recommender system
FACULTEIT WETENSCHAPPEN
• Database • Algorithms
Recommender system > CBF
FACULTEIT WETENSCHAPPEN
Recommender system > CF
FACULTEIT WETENSCHAPPEN
Black box problem
FACULTEIT WETENSCHAPPEN
Explanation system
FACULTEIT WETENSCHAPPEN
Explanation system > Examples
FACULTEIT WETENSCHAPPEN
Explanation system > evaluation
FACULTEIT WETENSCHAPPEN
FACULTEIT WETENSCHAPPEN
Explanation system > evaluation
Objective
FACULTEIT WETENSCHAPPEN
• Make a visualization...that can explain music suggestions
• Interactive• Steer the process (if possible)• Evaluation based on previously described aims• Non-professional users (learnability)
• Varying levels of perceived usefulness• SUS score of 80.5 for iteration 4• Learnability can improve• Design can be effective for explaining
collaborative recommendations• Starting point for further exploration
FACULTEIT WETENSCHAPPEN
Conclusion > Future work
• Visualization– Use symmetry in data to retain users instead of artists as nodes– Additional interactions (e.g. edges)– Clutter reduction through opacity– Temporary hide users
• Data– Improve data load times through caching
• Learnability– Further improve labels and visual clues