Topic Oriented User Influence Analysis in Social Networks

Social networks are widely used to organize events and activities for a group of users, so they can provide an opportunity of enhancing the group recommendation. As there are kinds of information on different topics in social networks, it is important to analyze the topical user influence. In this paper, we propose a topic oriented user influence analysis for group recommendation. Firstly, we consider that each user has different influences on different topics, so we calculate the user topical influence on different topics. Secondly, we construct a number of topical sub-groups depending on topics, and we use four user-factors to calculate the user social influence on these topical sub-groups more accurately. Thirdly, the user topical influence analysis is used to calculate the predicted rating of the topical sub-group by aggregating weighted ratings of all users in the sub-group. Finally, the experimental results demonstrate the effectiveness and efficiency of our topic-oriented user influence analysis method, which can improve the recommendation accuracy for the group.