Link prediction in social networks using Bayesian networks

Abstract

Link prediction is as an effective technique in social network analysis to find out the relations between users and has received great concentration by many researchers in recent studies. In this paper a method is proposed for friend recommendation in social networks using Bayesian networks. The Bayesian network is a reliable model to understand the relations between variables and has been used in many areas for prediction. This method with considering effective features on creating friendships, suggests friends to users accurately. First, the goal is to find attributes and similarities that have the most effect on creating a friendship. After that friends with most common similarities will be suggested to each other. The results of the proposed method are compared with those obtained from different algorithms like Friend Of Friend and it is found that the method used in this paper significantly improves the accuracy of friend suggestion due to inclusion of several features.