Integrating User Preference with Theft Identification and Profile Changer in LBSNs

Abstract

The popularity of GPS-equipped smart phones, Location Based Social Networks has gained popularity in recent years. In LBSNs, users not only engage themselves in chatting with friends ,sharing pictures but also with physical Place of Interest(POIs) showing their presence by leaving comments. These features of users provide an opportunity to understand the spatial and temporal characteristics of user activity (STAP). However, modeling such user-specific STAP needs to tackle high-dimensional data, i.e., user-location-time-activity quadruples, which is complicated and usually suffers from a data sparsity problem. In order to address this problem, a STAP model is proposed. It first models the spatial and temporal activity preference separately, and then uses a principle way to combine them for preference inference. In order to characterize the impact of spatial features, the personal functional regions and related parameters infer user spatial activity preference. In order to model the user temporal activity preference , the temporal activity similarity among different users are exploited .Finally, a context aware fusion framework is put forward to combine the spatial and temporal activity preference. The theft identification framework model and profile building application is implemented as a background service and it runs regularly on the device. This LSBN service is modeled as a light weight implementation so as to consume less battery and memory for multiple location based services.