A Resource Recommendation Method Based on User Taste Diffusion Model in Folksonomies

Collaborative tagging has been very popular with the development of the Web 2.0, which helps users manage, share and utilize resources effectively. For various kinds of resources, the way to recommend appropriate resources to right users is the key problem in tagging system. This paper proposes a user taste diffusion model based on the tripartite hypergraph to deal with the tri-relation of user-resource-tag in folksonomies and the data sparsity problem in personalized recommendation. Through the defined tri-relation model and diffusion probability matrix, the user's taste is diffused from itself to other users, resources and tags. When diffusion stops, the candidate resources can be identified then be ranked according to the taste values. As a result the top resources that have not been collected by the given user are selected as the final recommendations. Benefiting from the introduction of iterative diffusion mechanism, the recommendation results not only cover the resources collected by the given user's direct neighbors but also cover the ones which are collected by his/her extended neighbors. Experimental results show that our method performs better in terms of precision and recall than other recommendation methods.

[1]  Nigel Shadbolt,et al.  A Study of User Profile Generation from Folksonomies , 2008, SWKM.

[2]  Gediminas Adomavicius,et al.  Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions , 2005, IEEE Transactions on Knowledge and Data Engineering.

[3]  Tao Li,et al.  Recommendation model based on opinion diffusion , 2007, ArXiv.

[4]  Guido Caldarelli,et al.  Random hypergraphs and their applications , 2009, Physical review. E, Statistical, nonlinear, and soft matter physics.

[5]  Valentin Robu,et al.  The complex dynamics of collaborative tagging , 2007, WWW '07.

[6]  Jonathan L. Herlocker,et al.  Evaluating collaborative filtering recommender systems , 2004, TOIS.

[7]  Gerard Salton,et al.  A vector space model for automatic indexing , 1975, CACM.

[8]  Daniel Dajun Zeng,et al.  Collaborative filtering in social tagging systems based on joint item-tag recommendations , 2010, CIKM.

[9]  Hsinchun Chen,et al.  Applying associative retrieval techniques to alleviate the sparsity problem in collaborative filtering , 2004, TOIS.

[10]  Tereza Iofciu,et al.  Finding Communities of Practice from User Profiles Based on Folksonomies , 2006, EC-TEL Workshops.

[11]  Jian-Guo Liu,et al.  Improved collaborative filtering algorithm via information transformation , 2007, 0712.3807.

[12]  Ching-Yung Lin,et al.  Personalized recommendation driven by information flow , 2006, SIGIR.

[13]  Daniel Dajun Zeng,et al.  A Novel Recommendation Framework for Micro-Blogging Based on Information Diffusion , 2009, WITS 2009.

[14]  Lars Schmidt-Thieme,et al.  Tag-aware recommender systems by fusion of collaborative filtering algorithms , 2008, SAC '08.

[15]  Yi-Cheng Zhang,et al.  Bipartite network projection and personal recommendation. , 2007, Physical review. E, Statistical, nonlinear, and soft matter physics.

[16]  Andreas Hotho,et al.  Social Tagging Recommender Systems , 2011, Recommender Systems Handbook.

[17]  Shinichi Honiden,et al.  Web Page Recommender System based on Folksonomy Mining for ITNG ’06 Submissions , 2006, Third International Conference on Information Technology: New Generations (ITNG'06).

[18]  Richi Nayak,et al.  Collaborative Filtering Recommender Systems Using Tag Information , 2008, 2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology.

[19]  Yi-Cheng Zhang,et al.  Personalized Recommendation via Integrated Diffusion on User-Item-Tag Tripartite Graphs , 2009, ArXiv.

[20]  Andreas Hotho,et al.  Tag Recommendations in Folksonomies , 2007, LWA.

[21]  Fan Yang,et al.  An Adaptive Spreading Activation Scheme for Performing More Effective Collaborative Recommendation , 2005, DEXA.