Exploiting Category-Level Multiple Characteristics for POI Recommendation

Abstract

Point of interest (POI) recommendation has received significant attention in recent years, most existing studies exploit multiple auxiliary information to alleviate the problem of data sparsity, and consider the sequential features of user mobility. However, few studies consider the category-level characteristics derived from each user's historical check-in frequencies, and the characteristics between different latent factors. In this paper, we exploit category-level multiple characteristics to generate recommendation. First, we obtain the frequency characteristics by in-depth analysis of the historical check-in frequencies for different categories by each user, and propose a scheme including KL-divergence and text analysis algorithm. Then we propose a category-level sequential- and non-sequential influence-aware probabilistic generative model (CSNS), which models the characteristics (correlation and indeterminate decisiveness) between user latent behavior topics and latent sequence patterns. We design two stages to generate recommendations. In the first stage, CSNS and frequencies characteristics are exploited jointly to recommend the POI categories that users may visit. In the second stage, we depend on user profiles and poi features, and sort the candidate POI sets by combining the POI categories provided in the first stage. Comprehensive experiments on two real-world datasets demonstrate that our method outperforms the existing state-of-the-art POI recommendation models.