Content-Aware Point of Interest Recommendation on Location-Based Social Networks

The rapid urban expansion has greatly extended the physical boundary of users ’ living area and developed a large number of POIs (points of interest). POI rec-ommendation is a task that facilitates users ’ urban ex-ploration and helps them filter uninteresting POIs for decision making. While existing work of POI recom-mendation on location-based social networks (LBSNs) discovers the spatial, temporal, and social patterns of user check-in behavior, the use of content information has not been systematically studied. The various types of content information available on LBSNs could be re-lated to different aspects of a user’s check-in action, pro-viding a unique opportunity for POI recommendation. In this work, we study the content information on LB-SNs w.r.t. POI properties, user interests, and sentiment indications. We model the three types of information under a unified POI recommendation framework with the consideration of their relationship to check-in ac-tions. The experimental results exhibit the significance of content information in explaining user behavior, and demonstrate its power to improve POI recommendation performance on LBSNs