Personalized recommendation via integrated diffusion on user-item-tag tripartite graphs

Personalized recommender systems are confronting great challenges of accuracy, diversification and novelty, especially when the data set is sparse and lacks accessorial information, such as user profiles. item attributes and explicit ratings. Collaborative lags contain rich information about personalized preferences and item contents, and are therefore potential to help in providing better recommendations In this article, we propose a recommendation algorithm based on an integrated diffusion oil user-item-tag tripartite graphs We use three bench mark data sets, Del. icio us. MovieLens a rid BibSonomy, to evaluate our algorithm. Experimental results demonstrate that the usage of tag information call significantly improve accuracy. diversification and novelty of recommendations. (C) 2009 Elsevier B.V. All rights reserved.