The role of transparency in recommender systems
CHI '02 Extended Abstracts on Human Factors in Computing Systems
Is seeing believing?: how recommender system interfaces affect users' opinions
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
IEEE Transactions on Knowledge and Data Engineering
Evaluating SuperMusic: streaming context-aware mobile music service
ACE '08 Proceedings of the 2008 International Conference on Advances in Computer Entertainment Technology
Mixing it up: recommending collections of items
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Rush: repeated recommendations on mobile devices
Proceedings of the 15th international conference on Intelligent user interfaces
| Hi-index | 0.00 |
Mobile music consumption is increasing and many of the current mobile phones already offer music listening capabilities. Still, most of the current automatic playlist generation systems do not function in the mobile domain. This paper presents an evaluation of a content-based prototype mobile playlist generator. A user study was conducted to find out the quality and performance of our content-based automatic playlist generation engine from the user's perspective. In addition, possible benefits, usage scenarios, and future improvements are covered in this study, to support further development. There were 30 test subjects taking part in the usability study consisting of individual interviews and a trial. The overall performance of the automatic playlist generator satisfied 90% of the test subjects and they would like to use such system. Still, there are many improvements and new design ideas to take into account in further development to gain even better user acceptance and performance. These development ideas include e.g. getting rid of the most unsuccessful recommendations, providing option to group similar artists on the playlists and adding support for new ways of creating playlists by utilizing multiple seed songs.