Exploring Prior Knowledge from Human Mobility Patterns for POI Recommendation

• Published in: Applied sciences 2023-05, Vol.13 (11), p.6495
• Main Authors: Song, Jingbo, Yi, Qiuhua, Gao, Haoran, Wang, Buyu, Kong, Xiangjie
• Format: Article
• Language: English
• Subjects: Algorithms; Analysis; Datasets; Deep learning; graph neural network; Graph neural networks; human mobility pattern; Internet of Things; Knowledge; Mining; Mobility; Neural networks; POI recommendation; Recommender systems; Social networks; Social organization; Sparsity; Tourism; Traffic; Travel; Travel industry; Travel patterns; Urban environments
• ISSN: 2076-3417; 2076-3417
• DOI: 10.3390/app13116495

Point of interest (POI) recommendation is an important task in location-based social networks. It plays a critical role in smart tourism and makes it more likely for tourists to have personalized travel experiences. However, most current recommendation methods are based on learning the users’ check-in history and the users’ relationship network in the social network to make recommendations.Therefore, urban crowds’ regular travel patterns cannot be effectively utilized. In this paper, we propose a POI recommendation algorithm (HMRec) based on prior knowledge of human mobility patterns to solve this problem. Specifically, we propose the Human Mobility Pattern Extraction (HMPE) framework, which utilizes graph neural networks as extractors for human mobility patterns. The framework incorporates attention mechanisms to capture spatio-temporal information in urban traffic patterns. HMPE employs downstream tasks and design upsampling modules to reconstruct representation vectors for task objectives, enabling end-to-end training of the framework and obtaining pre-trained parameters for the human mobility pattern extractor. Furthermore, we introduce the Human Mobility Recommendation (HMRec) algorithm, which improves feature cross-interactions in the breadth model and incorporates prior knowledge of human patterns. This ensures that the recommendation results align more closely with human travel patterns in urban environments. Comparative experiments conducted on the Foursquare dataset demonstrate that HMRec outperforms baseline models with an average performance improvement of approximately 3%. Finally, we discuss existing challenges and future research directions, including approaches to address the issue of data sparsity.