Modeling User Contextual Behavior Semantics with Geographical Influence for Point-Of-Interest Recommendation
Dongjin Yu, Kaihui Xu, Dongjing Wang · Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering · 2019
Point-Of-Interest (POI) recommendation assists users to find their preferred places and helps businesses to attract potential customers.However, the data sparsity and the complexity of user check-in behavior pose a big challenge to POI recommender systems.To tackle this challenge, we propose a POI recommendation method named HeteGeoRankRec based on user contextual behavior semantics.First, to mine the fine-grained user behavioral features, we employ the meta path of Heterogeneous Information Network (HIN) to represent the complex semantic relationship among users and POIs and integrate the context constraints (such as time and weather) into the meta paths.Secondly, we propose a weighted matrix factorization model considering the influence of geographical distance to obtain semantic preference through the user-POI semantic correlativity matrixes generated by multiple meta paths.Finally, we introduce a ranking-based fusion method, which unifies the recommendation results of different meta paths as the final preference of users.Experiments on the real data collected from Foursquare show that HeteGeoRankRec has the better performance than the state-ofthe-art baselines.