目前,音乐越来越受到人们的青睐。如何为用户推荐符合用户需求的歌曲成为了很多音乐网站、电台以及其他相关音乐媒介关心的话题。针对这个问题,该文选取了社会化标签作为推荐方法的主要依据,首先将其分别映射到流派、情感和上下文信息三个语义空间中,然后在三个空间分别计算用户和歌曲的相似度,最后通过不同方法将三个空间的相似度进行融合从而对用户进行歌曲推荐。实验表明,融合不同空间相似度的推荐方法得到了很好的效果。
Abstract
Currently, music recommendation is a hot topic for lots of music sites, radio and other music medias. To address this issue, we take the social tags as the main resources of recommending methods, and map the tags into three semantic spaces which include genre, emotion and context. Then we calculate the similarity of users and tracks in each space. At last, we merge the similarities in three spaces with different methods to recommend the right tracks to users. The experiments show that the recommending method of merging different spaces similarities gets a good result.
关键词
音乐推荐 /
社会化标签 /
语义空间
{{custom_keyword}} /
Key words
music recommendation /
social tags /
semantic spaces
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Dwyer C, Hiltz S R, Passerini K. Trust and Privacy Concern Within Social Networking Sites: A Comparison of Facebook and MySpace[C]//Proceedings of the 13th Americas Conference on Information Systems(AMCIS 2007). Keystone, Colorado, 2007.
[2] Acquisti A and Gross R. Imagined Communities: Awareness Information Sharing and Privacy on the Facebook[C]//Proceedings of the 6th Workshop on Privacy Enhancing Technologies. Cambridge, UK. 2006: 36-58.
[3] Celma O and Lamere P. Music Recommendation Tutorial[C]//Proceedings of the 16th ACM International Conference on Multimedia. New York, NY, USA. 2008: 1157-1158.
[4] Nanopoulos A, Rafailidis D and Symeonidis P et al. MusicBox: Personalized Music Recommendation Based on Cubic Analysis of Social Tags[J]. Audio, Speech, and Language Processing, IEEE Transactions. 2010. 18(2): 407-412.
[5] Symeonidis P, Ruxanda M and Nanopoulos A et al. Ternary semantic analysis of social tags for personalized music recommendation[C]//Proceedings of the ISMIR. Philadelphia, USA. 2008: 219-224.
[6] Liang H, Xu Y and Li Y et al. Collaborative Filtering Recommender Systems Using Tag Information[C]//Proceedings of the Web Intelligence and Intelligent Agent Technology. Sydney, Australia. 2008: 59-62.
[7] Shepitsen A, Gemmell J, and Mobasher B et al. Personalized recommendation in social tagging systems using hierarchical clustering[C]//Proceedings of the 2008 ACM Conference on Recommender Systems(RecSys 08). New York, NY, USA. 2008: 259-266.
[8] Cai R, Zhang C and Wang C et al. MusicSense: contextual music recommendation using emotional[C]//Proceedings of the 15th International Conference on Multimedia Allocation Modeling. New York, NY, USA. 2007: 553-556.
[9] Tatli I, Birturk A. A Tag-Based Hybrid Music Recommendation System Using Semantic Relations and Multi-domain Information[C]//Proceedings of the Data Mining Workshops (ICDMW), 2011 IEEE 11th International Conference. Angeles, CA, USA. 2011: 548-554.
[10] Strapparava C, Mihalcea R. Learning to identify emotions in text[C]//Proceedings of the 2008 ACM Symposium on Applied Computing. New York, USA. 2008: 1556-1560.
[11] 阿培丁. 机器学习导论[M]. 机械工程出版社, 2009: 135-141.
[12] Cortes C, Vapnik V. Support-Vector Networks[J]. Machine Learning. 1995. 20(3): 273-297.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(60973068);教育部博士点基金(2009004111002)
{{custom_fund}}
PDF(733 KB)
