User Identification for Enhancing Recommendation by Social Media

With the eye-catching development of the Internet, new television technologies such as bi-directional Set-Top Box (STB) are appearing. Moreover, the studies of program recommendation based on STB are beginning to gather momentum. Previous methods mainly provide recommendations to TV users on the basis of regarding one account as one person, which ignores the feature of TV shared by more than one person in most instances. Again, the less interaction between TV and users makes personal information difficult to obtain or even not. In this paper, we propose a method to identify users in a single account by taking advantage of social media data and community detection algorithm. By collecting the information of specific micro-blog users related to program and program type label from Electronic Program Guide (EPG), program-based network diagrams are constructed to carry out user identification through community detection algorithm. Hereafter, we use the same recommended method for comparison experiments. Results show that the performance of recommendation applying the proposed method is more effectively than previous approaches.