An empirical study of topic-sensitive probabilistic model for expert finding in question answer communities

Abstract

In this article, we study the problem of finding experts in community question answering (CQA). Most of the existing approaches attempt to find experts in CQA via link analysis. One primary challenge of expert finding lies in that how to improve authority score ranking based on the user information. However, these existing link analysis techniques largely fail to consider the interests, expertise, and reputation of users (question askers and answerers). To address this limitation, we propose a topic-sensitive probabilistic model, by extending the PageRank algorithm, more effectively find in the community by incorporating link and user analysis into a unified framework. We have conducted extensive experiments using a real world data set from Yahoo! Answers of English language. Results show that our method significantly outperforms the existing link analysis techniques and advances the state-of-the-art performance on expert finding in CQA.