STARec: Adaptive Learning with Spatiotemporal and Activity Influence for POI Recommendation

Abstract

POI recommendation has become an essential means to help people discover attractive places. Intuitively, activities have an important impact on users’ decision-making, because users select POIs to attend corresponding activities. However, many existing studies ignore the social motivation of user behaviors and regard all check-ins as influenced only by individual user interests. As a result, they cannot model user preferences accurately, which degrades recommendation effectiveness. In this article, from the perspective of activities, this study proposes a probabilistic generative model called STARec. Specifically, based on the social effect of activities, STARec defines users’ social preferences as distinct from their individual interests and combines these with individual user activity interests to effectively depict user preferences. Moreover, the inconsistency between users’ social preferences and their decisions is modeled. An activity frequency feature is introduced to acquire accurate user social preferences because of close correlation between these and the key impact factor of corresponding check-ins. An alias sampling-based training method was used to accelerate training. Extensive experiments were conducted on two real-world datasets. Experimental results demonstrated that the proposed STARec model achieves superior performance in terms of high recommendation accuracy, robustness to data sparsity, effectiveness in handling cold-start problems, efficiency, and interpretability.

REFERENCES

1. [1] Aliannejadi Mohammad, Rafailidis Dimitrios, and Crestani Fabio. 2020. A joint two-phase time-sensitive regularized collaborative ranking model for point of interest recommendation. IEEE Trans. Knowl. Data Eng. 32, 6 (2020), 1050–1063.
2. [2] Arampatzis Avi and Kalamatianos Georgios. 2017. Suggesting points-of-interest via content-based, collaborative, and hybrid fusion methods in mobile devices. ACM Trans. Info. Syst. 36, 3 (2017), 1–28.
3. [3] Bao Jie, Zheng Yu, and Mokbel Mohamed F.. 2012. Location-based and preference-aware recommendation using sparse geo-social networking data. In Proceedings of the International Conference on Advances in Geographic Information Systems. ACM, New York, NY, 199–208.
4. [4] Blei David M., Ng Andrew Y., and Jordan Michael I.. 2003. Latent dirichlet allocation. J. Mach. Learn. Res. 3(Jan.2003), 993–1022.
5. [5] Campos Pedro G., Díez Fernando, and Cantador Iván. 2014. Time-aware recommender systems: A comprehensive survey and analysis of existing evaluation protocols. User Model. User-Adapt. Interact. 24, 1–2 (2014), 67–119.
6. [6] Chang Buru, Jang Gwanghoon, Kim Seoyoon, and Kang Jaewoo. 2020. Learning graph-based geographical latent representation for point-of-interest recommendation. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management. ACM, 135–144.
7. [7] Cheng Zhiyong, Chang Xiaojun, Zhu Lei, Kanjirathinkal Rose C., and Kankanhalli Mohan. 2019. MMALFM: Explainable recommendation by leveraging reviews and images. ACM Trans. Info. Syst. 37, 2 (2019), 1–28.
8. [8] Das Rajarshi, Zaheer Manzil, and Dyer Chris. 2015. Gaussian LDA for topic models with word embeddings. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. ACL, 795–804.
9. [9] Du Yulu, Meng Xiangwu, and Zhang Yujie. 2020. CVTM: A content-venue-aware topic model for group event recommendation. IEEE Trans. Knowl. Data Eng. 32, 7 (2020), 1290–1303.
10. [10] Ference Gregory, Ye Mao, and Lee Wang-Chien. 2013. Location recommendation for out-of-town users in location-based social networks. In Proceedings of the 22nd ACM International Conference on Information and Knowledge Management. ACM, New York, NY, 721–726.
11. [11] Gao Huiji, Tang Jiliang, Hu Xia, and Liu Huan. 2013. Exploring temporal effects for location recommendation on location-based social networks. In Proceedings of the 7th ACM Conference on Recommender Systems. ACM, New York, NY, 93–100.
12. [12] Kang Wangcheng and Mcauley Julian. 2018. Self-attentive sequential recommendation. In Proceedings of the IEEE International Conference on Data Mining (ICDM’18). IEEE, 197–206.
13. [13] Kong Dejiang and Wu Fei. 2018. HST-LSTM: A hierarchical spatial-temporal long-short term memory network for location prediction. In Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI’18). 2341–2347.
14. [14] Li Aaron Q., Ahmed Amr, Ravi Sujith, and Smola Alexander J.. 2014. Reducing the sampling complexity of topic models. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery, New York, NY, 891–900.
15. [15] Li Hui, Liu Ye, Mamoulis Nikos, and Rosenblum David S.. 2020. Translation-based sequential recommendation for complex users on sparse data. IEEE Trans. Knowl. Data Eng. 32, 8 (2020), 1639–1651.
16. [16] Li Ranzhen, Shen Yanyan, and Zhu Yanmin. 2018. Next point-of-interest recommendation with temporal and multi-level context attention. In Proceedings of the IEEE International Conference on Data Mining (ICDM’18). IEEE, 1110–1115.
17. [17] Li Xin, Jiang Mingming, Hong Huiting, and Liao Lejian. 2017. A time-aware personalized point-of-interest recommendation via high-order tensor factorization. ACM Trans. Info. Syst. 35, 4 (2017), 1–23.
18. [18] Lian Defu, Wu Yongji, Ge Yong, Xie Xing, and Chen Enhong. 2020. Geography-aware sequential location recommendation. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, New York, NY, 2009–2019.
19. [19] Liao Yi, Lam Wai, Bing Lidong, and Shen Xin. 2018. Joint modeling of participant influence and latent topics for recommendation in event-based social networks. ACM Trans. Info. Syst. 36, 3 (2018), 1–31.
20. [20] Liu Bin, Fu Yanjie, Yao Zijun, and Xiong Hui. 2013. Learning geographical preferences for point-of-interest recommendation. In Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, New York, NY, 1043–1051.
21. [21] Lu Yuanfu, Fang Yuan, and Shi Chuan. 2020. Meta-learning on heterogeneous information networks for cold-start recommendation. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, New York, NY, 1563–1573.
22. [22] Lv Pengtao and Meng Xiangwu. 2017. FeRe: Exploiting influence of multi-dimensional features resided in news domain for recommendation. Info. Process. Manage. 53, 5 (2017), 1215–1241.
23. [23] Lv Pengtao, Meng Xiangwu, and Zhang Yujie. 2019. BoRe: Adapting to reader consumption behavior instability for news recommendation. ACM Trans. Info. Syst. 38, 1 (2019), 1–33.
24. [24] Ma Yaxue, Mao Jin, Ba Zhichao, and Li Gang. 2020. Location recommendation by combining geographical, categorical, and social preferences with location popularity. Info. Process. Manage. 57, 4 (2020), 102251.
25. [25] Newman David, Karimi Sarvnaz, and Cavedon Lawrence. 2009. External evaluation of topic models. In Proceedings of the 14th Australasian Document Computing Symposium (ADCS’09). 1–8.
26. [26] Qian Tieyun, Liu Bei, Nguyen Quoc Viet Hung, and Yin Hongzhi. 2019. Spatiotemporal representation learning for translation-based POI recommendation. ACM Trans. Info. Syst. 37, 2 (2019), 1–24.
27. [27] Shi Chuan, Hu Binbin, Zhao Wayne Xin, and Philip S. Yu. 2018. Heterogeneous information network embedding for recommendation. IEEE Trans. Knowl. Data Eng. 31, 2 (2018), 357–370.
28. [28] Tang Jiaxi and Wang Ke. 2018. Personalized top-n sequential recommendation via convolutional sequence embedding. In Proceedings of the 7th ACM International Conference on Web Search and Data Mining. ACM, New York, NY, 565–573.
29. [29] Tierney Luke. 1994. Markov chains for exploring posterior distributions. Ann. Stat. 22, 4 (1994), 1701–1728.
30. [30] Wang Hongwei, Zhang Fuzheng, Wang Jialin, Zhao Miao, Li Wenjie, Xie Xing, and Guo Minyi. 2019. Exploring high-order user preference on the knowledge graph for recommender systems. ACM Trans. Info. Syst. 37, 3 (2019), 1–26.
31. [31] Wang Suhang, Wang Yilin, Tang Jiliang, Shu Kai, Ranganath Suhas, and Liu Huan. 2017. What your images reveal: Exploiting visual contents for point-of-interest recommendation. In Proceedings of the 26th International Conference on World Wide Web (WWW’17). 391–400.
32. [32] Wang Weiqing, Yin Hongzhi, Chen Ling, Sun Yizhou, Sadiq Shazia, and Zhou Xiaofang. 2015. Geo-SAGE: A geographical sparse additive generative model for spatial item recommendation. In Proceedings of 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, New York, NY, 1255–1264.
33. [33] Wang Weiqing, Yin Hongzhi, Sadiq Shazia, Chen Ling, Xie Min, and Zhou Xiaofang. 2016. Spore: A sequential personalized spatial item recommender system. In Proceedings of the 32nd IEEE International Conference on Data Engineering (ICDE’16). IEEE, 954–965.
34. [34] Wei Ling-Yin, Zheng Yu, and Peng Wen-Chih. 2012. Constructing popular routes from uncertain trajectories. In Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, New York, NY, 195–203.
35. [35] Xi Dongbo, Zhuang Fuzhen, Liu Yanchi, Zhu Hengshu, Zhao Pengpeng, Tan Chang, and He Qing. 2020. Exploiting bi-directional global transition patterns and personal preferences for missing POI category identification. Neural Netw. 132 (2020), 75–83.
36. [36] Xie Min, Yin Hongzhi, Wang Hao, Xu Fanjiang, Chen Weitong, and Wang Sen. 2016. Learning graph-based POI embedding for location-based recommendation. In Proceedings of the 25th ACM International on Conference on Information and Knowledge Management. ACM, New York, NY, 15–24.
37. [37] Yao Limin, Mimno David, and Mccallum Andrew. 2009. Efficient methods for topic model inference on streaming document collections. In Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, New York, NY, 937–946.
38. [38] Yao Zijun, Fu Yanjie, Liu Bin, Liu Yanchi, and Xiong Hui. 2016. POI recommendation: A temporal matching between POI popularity and user regularity. In Proceedings of the IEEE 16th International Conference on Data Mining. IEEE, 549–558.
39. [39] Ye Mao, Yin Peifeng, Lee Wang-Chien, and Lee Dik-Lun. 2011. Exploiting geographical influence for collaborative point-of-interest recommendation. In Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, New York, NY, 325–334.
40. [40] Yin Hongzhi, Cui Bin, Chen Ling, Hu Zhiting, and Zhang Chengqi. 2015. Modeling location-based user rating profiles for personalized recommendation. ACM Trans. Knowl. Discov. Data 9, 3 (2015), 19:1–19:41.
41. [41] Yin Hongzhi, Cui Bin, Zhou Xiaofang, Wang Weiqing, Huang Zi, and Sadiq Shazia. 2016. Joint modeling of user check-in behaviors for real-time point-of-interest recommendation. ACM Trans. Info. Syst. 35, 2 (2016), 1–44.
42. [42] Yin Hongzhi, Wang Weiqing, Wang Hao, Chen Ling, and Zhou Xiaofang. 2017. Spatial-aware hierarchical collaborative deep learning for POI recommendation. IEEE Trans. Knowl. Data Eng. 29, 11 (2017), 2537–2551.
43. [43] Yin Hongzhi, Zhou Xiaofang, Cui Bin, Wang Hao, Zheng Kai, and Nguyen Quoc Viet Hung. 2016. Adapting to user interest drift for POI recommendation. IEEE Trans. Knowl. Data Eng. 28, 10 (2016), 2566–2581.
44. [44] Ying Haochao, Zhuang Fuzhen, Zhang Fuzheng, Liu Yanchi, Xu Guandong, Xie Xing, Xiong Hui, and Wu Jian. 2018. Sequential recommender system based on hierarchical attention networks. In Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI’18). 3926–3932.
45. [45] Yu Fuqiang, Cui Lizhen, Guo Wei, Lu Xudong, Li Qingzhong, and Lu Hua. 2020. A category-aware deep model for successive POI recommendation on sparse check-in data. In Proceedings of the Web Conference. ACM, New York, NY, 1264–1274.
46. [46] Yuan Jinhui, Gao Fei, Ho Qirong, Dai Wei, Wei Jinliang, Zheng Xun, Xing Eric P., Liu Tieyan, and Ma Weiying. 2015. LightLDA: Big topic models on modest compute clusters. In Proceedings of the 24th International Conference on World Wide Web (WWW’15). 1351–1361.
47. [47] Yuan Quan, Cong Gao, and Lin Chin-Yew. 2014. COM: A generative model for group recommendation. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, New York, NY, 163–172.
48. [48] Yuan Quan, Cong Gao, Ma Zongyang, Sun Aixin, and Thalmann Nadia Magnenat. 2013. Time-aware point-of-interest recommendation. In Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, New York, NY, 363–372.
49. [49] Zhang Daniel, Wang Dong, Zheng Hao, Mu Xin, Li Qi, and Zhang Yang. 2017. Large-scale point-of-interest category prediction using natural language processing models. In Proceedings of the IEEE International Conference on Big Data (BigData’17). IEEE, 1027–1032.
50. [50] Zhang Jia-Dong and Chow Chi-Yin. 2015. CoRe: Exploiting the personalized influence of two-dimensional geographic coordinates for location recommendations. Info. Sci. 293 (2015), 163–181.
51. [51] Zhang Jia-Dong and Chow Chi-Yin. 2015. Spatiotemporal sequential influence modeling for location recommendations: A gravity-based approach. ACM Trans. Intell. Syst. Technol. 7, 1 (2015), 1–25.
52. [52] Zhang Jia Dong and Chow Chi Yin. 2016. CRATS: An LDA-based model for jointly mining latent communities, regions, activities, topics, and sentiments from geosocial network data. IEEE Trans. Knowl. Data Eng. 28, 11 (2016), 2895–2909.
53. [53] Zhang Jia-Dong, Chow Chi-Yin, and Jin Xu. 2017. Enabling kernel-based attribute-aware matrix factorization for rating prediction. IEEE Trans. Knowl. Data Eng. 29, 4 (2017), 798–812.
54. [54] Zhang Jia-Dong, Chow Chi-Yin, and Li Yanhua. 2014. LORE: Exploiting sequential influence for location recommendations. In Proceedings of the 22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. ACM, New York, NY, 103–112.
55. [55] Zhou Xiao, Mascolo Cecilia, and Zhao Zhongxiang. 2019. Topic-enhanced memory networks for personalised point-of-interest recommendation. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, New York, NY, 831–840.

Index Terms

• Applied computing

  • Law, social and behavioral sciences

    • Sociology

• Information systems

  • Information systems applications

    • Data mining

      • Collaborative filtering