Social Link Prediction Based on the Users' Information Transfer

Link prediction is one of the hotspots in social network analysis. However, traditional prediction method based on node similarity of network topology does not take the characteristics of user-generated content into account. In this article, the user-generated content based on traditional link prediction method is introduced to predict new user relationships through common neighbors in the social networks. This method is an information-theoretic measure with a predictive interpretation that directly quantifies the strength of the effect of one user's content on another's. Experimental results show that content transfer combined with topology is more consistent with the real social network, which has better performance in link prediction.