Exploring the Context of Locations for Personalized Location Recommendations

Abstract

Conventional location recommendation models rely on users' visit history, geographical influence, temporal influence, etc., to infer users' preferences for locations. However, systematically modeling a location's context (i.e., the set of locations visited before or after this location) is relatively unexplored. In this paper, by leveraging the Skip-gram model, we learn the latent representation for a location to capture the influence of its context. A pair-wise ranking loss that considers the confidences of observed user preferences for locations is then proposed to learn users' latent representations for personalized top-N location recommendations. Moreover, we also extend our model by taking into account temporal influence. Stochastic gradient descent based optimization algorithms are developed to fit the models. We conduct comprehensive experiments over four real datasets. Experimental results demonstrate that our approach significantly outperforms the state-of-the-art location recommendation methods.