A Fuzzy Rule-based Classification Approach to Friendship Recommendation in Social Networks

today, social networks have got an important part of online activities on the Web. The purpose of this work is design and implementation of a system to identify the possibility of friendship in social networks based on the fuzzy categorization of meetings. The most social networking suggestions are according to emails stored in the users' inbox, membership in groups, or friends of the user's friends, and these suggested people may not have any common features. Detection of the likelihood of being distinguished is one of the main goals of the research. In this study, it is attempted to introduce a fuzzy rule-based classification system, as well as a tunning rule-weighting mechanism, to provide a friend suggestion system in social networks based on user profile information. The experimental results indicate that the proposed system is significantly better than its counterparts in terms of prediction accuracy.