User communities and contents co‐ranking for user‐generated content quality evaluation in social networks

Summary With the massive popularity of social networks, more and more users can produce millions of user‐generated contents (UGCs) daily. However, UGC quality is uneven, which has posed challenges to finding superior contents in such a large data set. In this paper, we present a new idea of UGC quality evaluation exploiting user communities, which are formed by users either in a friend circle or with similar interests in social networks. The intuition is that a user community can help evaluate the UGC quality better than a single user. Hence, we propose a new graph‐theoretic user communities and contents co‐ranking (UCCC) algorithm for UGC quality evaluation. UCCC evaluates UGCs and their related user communities simultaneously based on three different relationship networks: the network connecting UGCs, the network connecting user communities, and a third network that ties the two together. Contents and user communities are ranked following a co‐ranking algorithm based on the assumption that there is a mutually reinforcing relationship between them. Experiments using real‐world data have shown that UCCC outperforms competitive algorithms by a good margin in most cases and a user community is more useful than a single user for UGC quality evaluation.