Considering periodic temporal behaviors and social relationships for next point-of-interest recommendation

doi:10.13474/j.cnki.11-2246.2025.1018

Abstract

Abstract: Next point-of-interest (POI)recommendation is one of the key applications in geolocation-based social networks.To address the issues of inadequate representation of users' cyclic temporal behavior and insufficient mining of social relationships in existing methods, this paper proposes a POI recommendation method that integrates both cyclic temporal behavior and social relationships.We analyze users' behavioral patterns from their check-in sequences across three time granularities: short-term, periodic, and long-term, and extract cyclical time-sequential behavioral features.Additionally, we mine social relationships between users by examining the overlap in their check-in records and the similarity of their friends, extracting dual-layer social features.The method introduces feature fusion with an adaptive weight allocation strategy and calculates users' preference scores for POIs.Based on these scores, the next POI is recommended to the user.Experimental results on the Sina Weibo (Shanghai)and Foursquare (New York)datasets demonstrate that the proposed method significantly improves hit rate (HR)and normalized discounted cumulative gain (NDCG).

Key words: next point of interest recommendation, sequential behavior, attention mechanism, social relationships

CLC Number:

P208

HE Xuan, XU Shenghua, CHE Xianghong, WANG Zhuolu, TANG Qing, YANG Lan. Considering periodic temporal behaviors and social relationships for next point-of-interest recommendation[J]. Bulletin of Surveying and Mapping, 2025, 0(10): 106-113.

References

[1] HUANG Qunying,WONG D W S. Activity patterns,socioeconomic status and urban spatial structure:what can social media data tell us？[J]. International Journal of Geographical Information Science,2016,30(9):1873-1898. [2] GAO K,YANG X,WU C,et al. Exploiting location-based context for POI recommendation when traveling to a new region[J]. IEEE Access,2020,8:52404-52412. [3] NOULAS A,SCELLATO S,MASCOLO C,et al. Exploiting semantic annotations for clustering geographic areas and users in location-based social networks[J]. Proceedings of 2011 International AAAI Conference on Web and Social Media,2011,5(3):32-35. [4] ELMAN J L. Finding structure in time[J]. Cognitive Science,1990,14(2):179-211. [5] HOCHREITER S. Long short-term memory[J]. Neural Computation,1997,9(8):1735-1780. [6] CHUNG J,GULCEHRE C,CHO K,et al. Empirical evaluation of gated recurrent neural networks on sequence modeling[EB/OL]. [2024-12-05]. https://arxiv.org/abs/1412.3555v1. [7] YING H,ZHUANG F,ZHANG F,et al. Sequential recommender system based on hierarchical attention network[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence. [S. l. ]:ACM Press,2018. [8] LIAN Defu,WU Yongji,GE Yong,et al. Geography-aware sequential location recommendation[C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. Virtual Event CA USA:ACM Press,2020:2009-2019. [9] LIU Qiang,WU Shu,WANG Liang,et al. Predicting the next location:a recurrent model with spatial and temporal contexts[C]//Proceedings of the 30th AAAI Conference on Artificial Intelligence. [S. l. ]:AAAI,2016. [10] LUO Yingtao,LIU Qiang,LIU Zhaocheng. STAN:spatio-temporal attention network for next location recommendation[C]//Proceedings of 2021 Web Conference. Ljubljana Slovenia:ACM Press,2021:2177-2185. [11] ZHAO Pengpeng,LUO Anjing,LIU Yanchi,et al. Where to go next:a spatio-temporal gated network for next POI recommendation[J]. IEEE Transactions on Knowledge and Data Engineering,2022,34(5):2512-2524. [12] LONG J,CHEN T,HUANG N Q V,et al. Decentralized collaborative learning framework for next POI recommendation[J]. ACM Transactions on Information Systems,2023,41(3):1-25. [13] SAFAVI S,JALALI M,HOUSHMAND M. Toward point-of-interest recommendation systems:a critical review on deep-learning approaches[J]. Electronics,2022,11(13):1998. [14] XIA Bin,BAI Yuxuan,YIN Junjie,et al. MTPR:a multi-task learning based POI recommendation considering temporal check-ins and geographical locations[J]. Applied Sciences,2020,10(19):6664. [15] AN Jingmin,JIANG Wei,LI Guanyu. Bidirectional trust-enhanced collaborative filtering for point-of-interest recommendation[J]. Sensors,2023,23(8):4140.