多维度偏好建模的动态兴趣点群组推荐算法

doi:10.3778/j.issn.1673-9418.2207107

摘要/Abstract

摘要： 随着互联网数据信息的海量化和地理社交网络（GSNs）的不断发展，群组活动在社会生活中盛行，推荐问题的对象由个人向群组进行延伸，兴趣点（POI）群组推荐问题也逐渐成为研究的热点问题。由于GSNs中用户偏好的多因素影响和群组决策过程的复杂化，传统的方法已经不再适用。为了充分挖掘GSNs中用户偏好和模拟群组决策过程，以提高群组推荐的整体性能，提出了一种基于多维度偏好建模的动态兴趣点群组推荐方法。首先，结合时间因素和空间因素，根据用户行为活动记录计算用户偏好，并以群组为单位构建群组-兴趣点感知图；然后，加入协同用户的影响完成对用户群组偏好的建模，并充分考虑了GSNs中的特征，保证了兴趣点推荐的准确性；最后，利用神经网络结构模拟群组决策过程，完成对兴趣点群组推荐任务的求解。在真实数据集上与现有的群组推荐算法进行了对比，实验结果表明提出的算法在兴趣点命中率等方面明显优于对照算法，证明了该算法的有效性。

关键词: 兴趣点群组推荐, 神经网络结构, 地理社交网络

Abstract: With the massive quantification of networked data and the development of geo-social networks (GSNs), group activities are prevalent in people’s life. The objects of recommendation systems are extended from individ-uals to user groups. Point-of-interest (POI) group recommendation problem is also gradually known as a hot research topic. However, the traditional methods are not suitable for group recommendation in geographic social networks, due to the multifactorial influence of user preferences in GSNs and the complexity of the group decision-making process. To reveal user preferences and the effect of the group decision process on group recommendation, this paper proposes a neural network-based model for dynamic POI group recommendation by leveraging multi-dimensional user preference. Firstly, the proposed model combines temporal and spatial factors to calculate user preferences based on user behavior activity records and builds a group-point-of-interest perception graph with group as unit. Next, this paper adds the influence of collaborative users to model group preferences, which fully considers the characteristics of GSNs, to ensure the accuracy of POI group recommendation. Finally, a neural network-based model can be constructed to simulate group decision-making, which can ensure the accuracy of POI recommen-dations. This paper conducts extensive experiments by comparing the existing group recommendation algorithms on the real datasets to demonstrate the performance of the method proposed in this paper. Experimental results show that the proposed method is significantly better than the existing algorithms in terms of the hit rate of POI, which proves the effectiveness of the proposed algorithm.

Key words: point-of-interest group recommendation, neural network structure, geo-social networks

孙明阳, 马玉亮, 袁野, 王国仁. 多维度偏好建模的动态兴趣点群组推荐算法[J]. 计算机科学与探索, 2023, 17(10): 2478-2487.

SUN Mingyang, MA Yuliang, YUAN Ye, WANG Guoren. Dynamic POI Group Recommendation Based on Multi-dimensional User Preference Model[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(10): 2478-2487.

参考文献

[1] CHANEY A J B, GARTRELL M, HOFMAN J M, et al. A large-scale exploration of group viewing patterns[C]//Pro-ceedings of the 2014 ACM International Conference on Interactive Experiences for TV and Online Video，Newca-stle Upon Tyne, Jun 25-27, 2014. New York: ACM, 2014: 31-38.
[2] GUO C, LI B, TIAN X. Flickr group recommendation using rich social media information[J]. Neurocomputing, 2016, 204: 8-16.
[3] HERZOG D, W?RNDL W. A user study on groups inter-acting with tourist trip recommender systems in public spaces[C]//Proceedings of the 27th ACM Conference on User Modeling, Adaptation and Personalization, Larnaca, Jun 9-12, 2019. New York: ACM, 2019: 130-138.
[4] HE Z, CHOW C Y, ZHANG J D. GAME: learning grap-hical and attentive multi-view embeddings for occasional group recommendation[C]//Proceedings of the 43rd Intern-ational ACM SIGIR Conference on Research and Develop-ment in Information Retrieval, Jul 25-30, 2020. New York: ACM, 2020: 649-658.
[5] HE Z, CHOW C Y, ZHANG J D, et al. GRADI: towards group recommendation using attentive dual top-down and bottom-up influences[C]//Proceedings of the 2019 IEEE Int-ernational Conference on Big Data, Los Angeles, Dec 9-12, 2019. Piscataway: IEEE, 2019: 631-636.
[6] FAN W, MA Y, LI Q, et al. Graph neural networks for social recommendation[C]//Proceedings of the 2019 World Wide Web Conference, San Francisco, May 13-17, 2019.New York: ACM, 2019: 417-426.
[7] YU Z, ZHOU X, HAO Y, et al. TV program recommen-dation for multiple viewers based on user profile merging[J]. User Modeling and User-Adapted Interaction, 2006, 16(1): 63-82.
[8] BALTRUNAS L, MAKCINSKAS T, RICCI F. Group recom-mendations with rank aggregation and collaborative filter-ing[C]//Proceedings of the 2010 ACM Conference on Recommender Systems, Barcelona, Sep 26-30, 2010. New York: ACM, 2010: 119-126.
[9] AMER-YAHIA S, ROY S B, CHAWLAT A, et al. Group recommendation: semantics and efficiency[J]. Proceedings of the VLDB Endowment, 2009, 2(1): 754-765.
[10] CARVALHO L A M C, MACEDO H T. Users’ satisfaction in recommendation systems for groups: an approach based on noncooperative games[C]//Proceedings of the 22nd Inte-rnational Conference on World Wide Web, Rio de Janeiro, May 13-17, 2013. New York: ACM， 2013: 951-958.
[11] WANG J, JIANG Y, SUN J, et al. Group recommendation based on a bidirectional tensor factorization model[J]. World Wide Web, 2018, 21(4): 961-984.
[12] GUO J, ZHU Y, LI A, et al. A social influence approach for group user modeling in group recommendation systems[J]. IEEE Intelligent Systems, 2016, 31(5): 40-48.
[13] YIN H, WANG Q, ZHENG K, et al. Social influence-based group representation learning for group recommendation[C]//Proceedings of the 35th IEEE International Confer-ence on Data Engineering, Macao, China, Apr 8-11, 2019. Piscataway: IEEE, 2019: 566-577.
[14] VINH TRAN L, NGUYEN PHAM T A, TAY Y, et al. Interact and decide: Medley of sub-attention networks for effective group recommendation[C]//Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, Paris, Jul 21-25, 2019. New York: ACM, 2019: 255-264.
[15] CAO D, HE X, MIAO L, et al. Attentive group recom-mendation[C]//Proceedings of the 41st International ACM SIGIR Conference on Research & Development in Inform-ation Retrieval, Ann Arbor, Jul 8-12, 2018. New York: ACM, 2018: 645-654.
[16] CAO D, HE X, MIAO L, et al. Social-enhanced attentive group recommendation[J]. IEEE Transactions on Knowl-edge and Data Engineering, 2021, 33(3): 1195-1209.
[17] ZHU Q, WANG S, CHENG B, et al. Context-aware group recommendation for point-of-interests[J]. IEEE Access, 2018, 6: 12129-12144.
[18] SOJAHROOD Z B, TALEAI M. A POI group recom-mendation method in location-based social networks based on user influence[J]. Expert Systems with Applications, 2021, 171: 114593.
[19] 卢扬, 樊超, 韩筱璞, 等. 签到行为的可预测性及影响因素分析[J]. 电子科技大学学报, 2015, 44(2): 163-171.
LU Y, FAN C, HAN X P, et al. Predictability and influential factors on check-in behaviors[J]. Journal of University of Electronic Science and Technology of China, 2015, 44(2): 163-171.
[20] MCLAUGHLIN M R, HERLOCKER J L. A collaborative filtering algorithm and evaluation metric that accurately model the user experience[C]//Proceedings of the 27th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval， 2004: 329-336.
[21] HERLOCKER J L, KONSTAN J A, TERVEEN L G, et al. Evaluating collaborative filtering recommender systems[J]. ACM Transactions on Information Systems, 2004, 22(1): 5-53.
[22] HAMILTON W, YING Z, LESKOVEC J. Inductive repres-entation learning on large graphs[C]//Advances in Neural Information Processing Systems 30, Long Beach, Dec 4-9, 2017: 1024-1034.
[23] CHEN J, ZHANG H, HE X, et al. Attentive collaborative filtering: multimedia recommendation with item-and com-ponent-level attention[C]//Proceedings of the 40th Interna-tional ACM SIGIR Conference on Research and Develo-pment in Information Retrieval，Shinjuku, Aug 7-11, 2017. New York: ACM, 2017: 335-344.
[24] HE X, LIAO L, ZHANG H, et al. Neural collaborative filtering[C]//Proceedings of the 26th International Confer-ence on World Wide Web, Perth, Apr 3-7, 2017. New York:ACM, 2017: 173-182.
[25] WANG X, HE X, NIE L, et al. Item silk road: recom-mending items from information domains to social users[C]//Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, Shinjuku, Aug 7-11, 2017. New York: ACM, 2017: 185-194.