Personalized location recommendation by fusing sentimental and spatial context

Internet users would like to obtain interesting location information for a travel. With the rapid development of social media, many kinds of location recommender systems are proposed in recent years. Existing methods mostly focus on mining user check-in information that could be leveraged to understand their trajectories. However, the characteristics and attributes of geographical locations also play an important role in recommender systems. In this paper, sentimental attributes of locations are explored and we propose a Point of Interest (POI) mining method and a personalized recommendation model by fusing sentimental spatial context. First, a Sentimental–Spatial POI Mining (SPM) method is utilized to mine the POIs by fusing the sentimental and geographical attributes of locations. Second, we recommend the POIs to users by a Sentimental–Spatial POI Recommendation (SPR) model incorporating the factors of sentiment similarity and geographical distance. Last, the advantages and superior performance of our methods are demonstrated by extensive experiments on a real-world dataset.