Graph-Based Recommendation on Social Networks

Recommender systems have emerged as an essential response to the rapidly growing digital information phenomenon in which users are finding it more and more difficult to locate the right information at the right time. Systems under Web2.0 allow users not only to give resources- ratings but also to assign tags to them. Tags play a significant role in Web 2.0. They can be used for navigation, browsing, recommendation and so on. In this paper, we propose a novel recommendation algorithm, which is based on social networks. The social network is established among users and items, taking into account both the information of ratings and tags. We consider users´ co-tagging behaviors and add the similarity relationship to the graph to enhance the performance. Our algorithm is based on the Random Walk with Restarts but provides a more natural and efficient way to represent social networks. Having considered the influence of tags, the transition matrix is denser and the recommendation is more accurate. By evaluating our new algorithm and comparing it to the baseline algorithm which is used in many real world recommender systems on a real life dataset, we make the conclusion that our method performs better than the baseline method.