A music recommendation system based on music data grouping and user interests
Proceedings of the tenth international conference on Information and knowledge management
Labeling images with a computer game
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
| Hi-index | 0.00 |
The system "MusicTagger" is a game in which two players hear 30 seconds of a song, describe it independently and get points if they succeed in making the same descriptions. Additionally, it is a music recommendation system which compares songs with the help of the descriptions given in the game. MusicTagger is based on the principle of "human computation", meaning that problems (in this case, music recommendation) are solved by computers via eliciting human knowledge and making intelligent use of the aggregated information. This paper presents the design and implementation of the "MusicTagger" system together with results of an empirical lab study which demonstrates the potential of the recommendation engine.