Joint Geographical and Temporal Modeling based on Matrix Factorization for Point-of-Interest Recommendation

With the popularity of Location-based Social Networks, Point-of-Interest (POI) recommendation has become an important task, which learns the users' preferences and mobility patterns to recommend POIs. Previous studies show that incorporating contextual information such as geographical and temporal is necessary to improve POI recommendation and address the data sparsity problem. However, existing methods model the geographical influence based on the physical distance between POIs or users, while ignoring the temporal characteristics of the geographical influence. In this paper, we do a study on the user mobility patterns where we find out that users' check-ins happen around several centers depending on their current temporal state. Next, we propose a spatio-temporal activity centers algorithm to model users' behavior more accurately. Finally, we demonstrate the effectiveness of our proposed contextual model by incorporating it into the matrix factorization model under two different settings: i) static and ii) temporal. To show the effectiveness of our proposed method, which we refer to as STAMC, we conduct experiments on two well-known real-world datasets acquired from Gowalla and Foursquare LBSNs. Experimental results show that the STAMC model achieves statistically significant performance improvement, compared to sate-of-the-art techniques. Also, we demonstrate the effectiveness of geographical and temporal information for modeling users' activity centers and the importance of modeling them jointly.