A Paradigm of Temporal-Weather-Aware Transition Pattern for POI Recommendation

Abstract

Point of interest (POI) recommendation analyses user preferences through historical check-in data. However, existing POI recommendation methods often overlook the infiuence of weather information and face the challenge of sparse historical data for individual users. To address these issues, this paper proposes a new paradigm, namely temporal-weather-aware transition pattern for POI recommendation (TWTransNet). This paradigm is designed to capture user transition patterns under different times and weather conditions. Additionally, we introduce the construction of a user-POI interaction graph to alleviate the problem of sparse historical data for individual users. Furthermore, when predicting user interests by aggregating graph in-formation, some POIs may not be suitable for visitation under current weather conditions. To account for this, we propose an attention mechanism to filter POI neighbours when aggregating information from the graph, considering the impact of weather and time. Empirical results on two real-world datasets demonstrate the superior performance of our proposed method, showing a substantial improvement of 6.91%-23.31% in terms of prediction accuracy.

Keywords

data mining / decision making / multimedia

References

[1] B. Liu, Y. Fu, Z. Yao, and H. Xiong, “Learning Geographical Pref-erences for Point-of-Interest Recommendation,” in Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (ACM, 2013), 1043-1051.

[2] M. Ye, P. Yin, W.-C.Lee, and D.-L. Lee, “Exploiting Geographical Infiuence for Collaborative Point-of-Interest Recommendation,” in Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval (ACM, 2011), 325-334.

[3] R. Li, Y. Shen, and Y. Zhu, “Next Point-of-Interest Recommendation With Temporal and Multi-Level Context Attention,” in 2018 IEEE In-ternational Conference on Data Mining (ICDM) IEEE, 2018), 1110-1115.

[4] B. Chang, G. Jang, S. Kim, and J. Kang, “Learning Graph-Based Geographical Latent Representation for Point-of-Interest Recommen-dation,” in Proceedings of the 29th ACM International Conference on Information & Knowledge Management (ACM, 2020), 135-144.

[5] G. Suganeshwari and S. Syed Ibrahim, “A Survey on Collaborative Filtering Based Recommendation System,” in Proceedings of the 3rd International Symposium on Big Data and Cloud Computing Challenges (ISBCC-16’) (Springer, 2016),503-518.

[6] Q. Liu, S. Wu,L. Wang, and T. Tan, “Predicting the Next Location: A Recurrent Model With Spatial and Temporal Contexts,” in Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 30, No. 1 (AAAI, 2016), https://doi.org/10.1609/aaai.v30i1.9971.

[7] Y. Zhang, H. Dai, C. Xu, et al., “Sequential Click Prediction for Sponsored Search With Recurrent Neural Networks,” in Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 28, No. 1 (AAAI, 2014), https://doi.org/10.1609/aaai.v28i1.8917.

[8] J. Zhang, X. Liu, X. Zhou, and X. Chu, “Leveraging Graph Neural Networks for Point-of-Interest Recommendations,” Neurocomputing 462 (2021): 1-13, https://doi.org/10.1016/j.neucom.2021.07.063.

[9] N. Lim, B. Hooi, S.-K. Ng, et al., “STP-UDGAT: Spatial-Temporal-Preference User Dimensional Graph Attention Network for Next POI Recommendation,” in Proceedings of the 29th ACM International Con-ference on Information & Knowledge Management (ACM, 2020), 845-854.

[10] D. Lian, Y. Wu, Y. Ge, X. Xie and E. Chen, “Geography-Aware Sequential Location Recommendation ” in Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (ACM, 2020), 2009-2019.

[11] M. B. Hossain, M. S. Arefin, I. H. Sarker, M. Kowsher, P. K. Dhar, and T. Koshiba, “CARAN: A Context-Aware Recency-Based Attention Network for Point-of-Interest Recommendation,” IEEE Access 10 (2022): 36299-36310, https://doi.org/10.1109/access.2022.3161941.

[12] Y. Luo, Q. Liu, and Z. Liu, “STAN: Spatio-Temporal Attention Network for Next Location Recommendation,” in Proceedings of the Web Conference 2021 ACM, 2021), 2177-2185.

[13] Y. Li, T. Chen, Y. Luo, H. Yin, and Z. Huang, “Discovering Collaborative Signals for Next POI Recommendation With Iterative Seq2graph Augmentation,” arXiv preprint arXiv:2106. 15814 (2021): 1491-1497, https://doi.org/10.24963/ijcai.2021/206.

[14] D. Yang, B. Fankhauser, P. Rosso, and P. Cudre-Mauroux, “Location Prediction Over Sparse User Mobility Traces Using RNNS,” in Pro-ceedings of the 29 International Joint Conference on Artificial Intelligence (IJCAI, 2020), 2184-2190.

[15] S. Rendle, C. Freudenthaler, and L. Schmidt-Thieme, “Factorizing Personalized Markov Chains for Next-Basket Recommendation,” in Proceedings of the 19th International Conference on World Wide Web (ACM, 2010), 811-820.

[16] P. Zhao, A. Luo, Y. Liu, et al., “Where To Go Next: A Spatio-Temporal Gated Network for Next POI Recommendation,” IEEE Transactions on Knowledge and Data Engineering 34, no. 5 (2020): 2512-2524, https://doi.org/10.1109/tkde.2020.3007194.

[17] K. Sun, T. Qian, T. Chen, Y. Liang,Q. V. H. Nguyen, and H. Yin, “Where To Go Next: Modeling Long-and Short-Term User Preferences for Point-of-Interest Recommendation,” in Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34, No. 1 (AAAI, 2020), 214-221, https://doi.org/10.1609/aaai.v34i01.5353.

[18] J. Feng, Y. Li, C. Zhang, et al., “DeepMove: Predicting Human Mobility With Attentional Recurrent Networks,” in Proceedings of the 2018 World Wide Web Conference (ACM, 2018), 1459-1468.

[19] X. He, K. Deng, X. Wang, Y. Li, Y. Zhang, and M. Wang, “LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation,” in Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (ACM, 2020), 639-648.

[20] Q. Guo, Z. Sun, J. Zhang, and Y.-L. Theng, “An Attentional Recurrent Neural Network for Personalized Next Location Recom-mendation,” in Proceedings of the AAAI Conference on Artificial Intelli-gence, Vol. 34, No. 1 (AAAI, 2020), 83-90, https://doi.org/10.1609/aaai.v34i01.5337.

[21] C. Zuo, X. Zhang, L. Yan, and Z. Zhang, “GUGEN: Global User Graph Enhanced Network for Next POI Recommendation,” IEEE Transactions on Mobile Computing 23, no. 12 (2024): 14975-14986, https://doi.org/10.1109/tmc.2024.3455107.

[22] M. Acharya and K. K. Mohbey, “Time-Aware Cross-Domain Point-of-Interest Recommendation in Social Networks,” Engineering Appli-cations of Artificial Intelligence 139 (2025): 109630, https://doi.org/10.1016/j.engappai.2024.109630.

[23] J. Fu, R. Gao, Y. Yu, et al., “Contrastive Graph Learning Long and Short-Term Interests for POI Recommendation,” Expert Systems with Applications 238 (2024): 121931, https://doi.org/10.1016/j.eswa.2023.121931.

[24] B. A. Duncan, S. Kallumadi, T. Berg-Kirkpatrick, and J. Mcauley, “MAWI Rec: Leveraging Severe Weather Data in Recommendation,” in Proceedings of the 18th ACM Conference on Recommender Systems (ACM, 2024).

[25] A. Noorian, “A Personalized Context and Sequence Aware Point of Interest Recommendation,” Multimedia Tools and Applications 83, no. 32 (2024): 77565-77594, https://doi.org/10.1007/s11042-024-18522-3.

[26] J. Chen, W. Jiang, J. Wu, K. Li, and K. Li, “Dynamic Personalized POI Sequence Recommendation With Fine-Grained Contexts,” ACM Transactions on Internet Technology 23, no. 2 (2023): 1-28, https://doi.org/10.1145/3583687.

[27] Q. Guo, F. Zhuang, C. Qin, et al., “A Survey on Knowledge Graph-Based Recommender Systems,” IEEE Transactions on Knowledge and Data Engineering 34, no. 8 (2020): 3549-3568, https://doi.org/10.1109/tkde.2020.3028705.

[28] Z. Wang, J. Zhang,J. Feng, and Z. Chen, “Knowledge Graph Embedding by Translating on Hyperplanes,” in Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 28, No. 1 (AAAI, 2014), https://doi.org/10.1609/aaai.v28i1.8870.

[29] J. Wu, X. He, X. Wang, et al., “Graph Convolution Machine for Context-Aware Recommender System,” Frontiers of Computer Science 16, no. 6 (2022): 166614, https://doi.org/10.1007/s11704-021-0261-8.

[30] M. Unger and A. Tuzhilin, “Hierarchical Latent Context Repre-sentation for Context-Aware Recommendations,” IEEE Transactions on Knowledge and Data Engineering 34, no. 7 (2020): 3322-3334, https://doi.org/10.1109/TKDE.2020.3022102.

[31] N. R. Chopde and M. Nichat, “Landmark Based Shortest Path Detection by Using A* and Haversine Formula,” International Journal of Innovative Research in Computer and Communication Engineering 1, no. 2 (2013): 298-302, https://www.researchgate.net/profile/Mangesh-Nichat-2/publication/282314348_Landmark_based_shortest_path_detection_by_using_A_Algorithm_and_Haversine_Formula/links/56389bb708ae4bde5021b0f5/Landmark-based-shortest-path-detection-by-using-A-Algorithm-and-Ha.

[32] J. Schmidhuber and S. Hochreiter, “Long Short-Term Memory ” Neural Computation 9, no. 8 (1997): 1735-1780, https://doi.org/10.1162/neco.1997.9.8.1735.

[33] X. Kong, Z. Chen, J. Li, J. Bi, and G. Shen, “KGNext: Knowledge-Graph-Enhanced Transformer for Next POI Recommendation With Uncertain Check-Ins,” IEEE Transactions on Computational Social Systems 11, no. 5 (2024): 6637-6648, https://doi.org/10.1109/tcss.2024.3396506.

Funding

Stable Support Project of Shenzhen(20231120161634002)

Shenzhen Science and Technology Programme(JCYJ20240813141417023)

Natural Science Foundation of Guangdong Province of China(2025A1515010233)

Guangdong Provincial Department of Education(2024KTSCX060)

Tencent ‘Rhinoceros Birds’—Scientific Research Foundation for Young Teachers of Shenzhen University, Open Project of State Key Laboratory for Novel Software Technology of Nanjing University(KFKT2025B22)

Hong Kong RGC General Research Fund(152211/23E)

Hong Kong RGC General Research Fund(15216424/24E)

PolyU Internal Fund(P0043932)

PolyU Internal Fund(P0048988)

NVIDIA AI Technology Centre