SNS user classification and its application to obscure POI discovery

Abstract

Technologies are increasingly taking advantage of the explosion of social media (e.g., web searches, ad targeting, personalized geo-social recommendations, urban computing). Estimating the characteristics of users, or user profiling, is one of the key challenges for such technologies. This paper focuses on the important problem of automatically estimating social networking service (SNS) user with a given city, which can significantly improve location-based services and systems. The authority in our work measures a user's familiarity with a particular city. By analyzing users' social, temporal, and spatial behavior, we respectively propose and compare three models for user authority: a social-network-driven model, time-driven model, and location-driven model. Furthermore, we discuss the integration of these three models. Finally, by using these user-profiling models, we propose a new application for geo-social recommendations. In contrast to related studies, which focus on popular and famous points of interests (POIs), our models help discover obscure POIs that are not well known. Experimental evaluations and analysis on a real dataset collected from three cities demonstrate the performance of the proposed user-profiling models. To verify the effect of discovering obscure POIs, the proposed application was implemented to discover and explore obscure POIs in Kyoto, Japan.