Recommender system with formal concept analysis

This paper studies friends recommendations designed to help users find mind-like, offline contacts and discover new friends on social networking sites. We propose the CCG(concept context graph) to represent the knowledge context based on the user´s twitter and social interactions to recommend friends. By computing the concept similarity among the concepts in the concept context graph and matching users with the concept context graph, we compute the rank values of the target users for recommendation. Experimental evaluation was conducted in order to determine the impact of concept clustering means based on CCG. We found that the proposed method is satisfactory for effective and efficient followees recommendation.