Associative face co-occurrence networks for recommending friends in social networks

In social network services, which have become widely used as an important tool to share rich information, making new friends is the most basic functionality to enable users to take advantage of their social networks. However, in current social network services, making new friends still relies on manually browsing networks of current friends. Even though the most services try to automatically suggest new friends, users can hardly accept those suggestions without any meaningful explanation of relationships. To deal with this issue, in this paper, we look into personal photos as an additional source for social network analysis and analyze the potential of name tagging in the photos for applying to friend recommendations. Moreover, we propose a new compact data structure, namely Face Co-Occurrence Networks (FCON), for photo networks storing crucial and quantitative information about people appearance in photos. By incorporating with FCON, we discover strong associative relationships among people and recommend reliable social friends. Experimental results demonstrate the feasibility of our method for recommending friends in social network services.