A Topic-Specific Contextual Expert Finding Method in Social Network

Expert retrieval is a widely studied problem. However, most existing expert finding methods focus on social network which contains topic-irrelevant users and interactions. This results in that the expert results are not topic-specific and practical because many users need to find experts for certain topic. Furthermore, contextual factors of social network also affect the accuracy of expert finding and are seldom concerned comprehensively in existing approaches. To solve above problems, in this paper, we propose a topic-specific contextual expert finding method. At first, we define a topic-specific contextual feature model (TSCFM) which consists of a topic-aware model (TAM) for topical feature and a context-aware model (CAM) for contextual feature. TAM uses LDA and HITS to extract topical feature, and CAM evaluates social relation, time and location factors to extract contextual features. Then based on TSCFM, we learn an expert scoring function which synthetically concerns topical and contextual features using SVM algorithm and rank the experts. The experiments on two datasets demonstrate that our proposed expert finding method is feasible and can improve the accuracy.