gSCorr: Modeling Geo-Social Correlations for New Check-ins on Location-Based Social Networks

Location-based social networks (LBSNs) have attracted increasing users in recent years. The availability of geographical and social information of online LBSNs provides an unprecedented opportunity to study the human movement from their socio-spatial behavior, enabling a variety of locationbased services, from mobile marketing to disaster relief. Previous work on LBSNs attempts to utilize a user’s social network information for location prediction, with limited contribution from the information on social networks in explaining a user’s check-in behavior. As users can check-in at new places, traditional work on location prediction that relies on mining a user’s historical moving trajectories is not designed for the“cold start”problem predicting new check-ins. In this paper, we propose to utilize the social network information for solving the“cold start” location prediction problem, with a geo-social correlation model to capture social correlations on LBSNs with respect to social networks and geographical distance. The experimental results on a real-world LBSN demonstrate that our approach properly models the social correlations of a user’s new check-ins by considering various correlation strength and correlation metrics.