Personalized next-song recommendation in online karaokes
Authors:
Open Access
- 12 October 2013
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 137-140
Abstract
In this paper, we propose Personalized Markov Embedding (PME), a next-song recommendation strategy for online karaoke users. By modeling the sequential singing behavior, we first embed songs and users into a Euclidean space in which distances between songs and users reflect the strength of their relationships. Then, given each user's last song, we can generate personalized recommendations by ranking the candidate songs according to the embedding. Moreover, PME can be trained without any requirement of content information. Finally, we perform an experimental evaluation on a real world data set provided by ihou.com which is an online karaoke website launched by iFLYTEK, and the results clearly demonstrate the effectiveness of PME.Keywords
This publication has 13 references indexed in Scilit:
- Playlist prediction via metric embedding2012
- Yahoo! music recommendations2011
- Enhancing Collaborative Filtering by User Interest Expansion via Personalized RankingIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2011
- Factorizing personalized Markov chains for next-basket recommendation2010
- Context-aware query suggestion by mining click-through and session data2008
- Towards ensemble learning for hybrid music recommendation2007
- MusicSense2007
- Evaluating collaborative filtering recommender systemsACM Transactions on Information Systems, 2004
- An empirical study of smoothing techniques for language modelingComputer Speech & Language, 1999
- GroupLens1994