FAER: Fairness-Aware Event-Participant Recommendation in Event-Based Social Networks

Abstract

The e vent- b ased s ocial n etwork (EBSN) is a new type of social network that combines online and offline networks. In recent years, an important task in EBSN recommendation systems has been to design better and more reasonable recommendation algorithms to improve the accuracy of recommendation and enhance user satisfaction. However, the current research seldom considers how to coordinate fairness among individual users and reduce the impact of individual unreasonable feedback in group event recommendation. In addition, when considering the fairness to individuals, the accuracy of recommendation is not greatly improved by fully incorporating the key context information. To solve these problems, we propose a prefiltering algorithm to filter the candidate event set, a multidimensional context recommendation method to provide personalized event recommendations for each user in the group, and a group consensus function fusion strategy to fuse the recommendation results of the members of the group. To improve overall satisfaction with the recommendations, we propose a ranking adjustment strategy for the key context. Finally, we verify the effectiveness of our proposed algorithm on real data sets and find that FAER is superior to the latest algorithms in terms of global satisfaction, distance satisfaction and user fairness.