PersoNet: Friend Recommendation System Based on Big-Five Personality Traits and Hybrid Filtering

Abstract

Friend recommendation system (FRS) is an essential part of any social network system. With the popularity of social network sites, many FRSs have been proposed in the past few years. However, most of them are homophily based systems, homophily is the propensity to associate and bond with similar others. In other words, these systems will recommend people that you share common features with them as friends. Homophily based FRS is accurate when the common feature is a physical or social feature, such as age, race, location, job, or lifestyle. However, it is not the case with personality types. Having a given personality type does not necessarily mean that you are compatible with people that have the same personality type. Therefore, in this paper, we present and evaluate an FRS based on the big-five personality traits model and hybrid filtering, in which the friend recommended process is based on personality traits and users' harmony rating. To validate the proposed system's accuracy, a personality-based social network site that uses the proposed FRS named PersoNet is implemented. Users' rating results show that PersoNet performs better than collaborative filtering (CF)-based FRS in terms of precision and recall.