Attention-aware Next Event Recommendation Strategy for Groups

doi:10.3778/j.issn.1673-9418.2107034

Abstract

Abstract: In recent years, event-based social networks (EBSN) have gradually become an effective way for people to choose social events, and how to accurately recommend events to users or groups in need has become an important topic in this field. Next item recommendation can capture users’ dynamic preferences and has been well developed in e-commerce and other fields. However, there are less researches on next event recommendation for groups in EBSN. This paper mainly studies the group-oriented next event recommendation strategy, but due to the dynamic change of group preference, short event life cycle and cold start of new events, it is more difficult to recommend the next event for groups. Firstly, based on the characteristic that group preferences change dynamically over time, the history interaction records of group are divided into each period. Considering the sparsity of the member data due to the period division, which is unfavorable to group preference modeling, an engagement-based ranking strategy is proposed to extract the preferences of core members in the current period, and the attention mechanism is used to fuse them to the group static preferences. Then, the group dynamic preference is obtained by combining the static preference of each period with the attention-based sequential model. Finally, the multi-label classification problem is introduced into the event recommendation, which regards the contexts as labels of the event, and makes the model predict the probability distribution of each context to match the event, so as to alleviate the new event cold start problem. Experimental results verify that the proposed strategy has good performance.

Key words: event-based social networks (EBSN), next event recommendation, group recommendation, attention mechanism, multi-label classification

摘要： 近年来，基于事件社会网络（EBSN）逐渐成为人们寻找感兴趣事件的有效途径，如何将事件精准地推荐给有需求的用户已成为该领域的重要主题。下一个项目推荐能够捕获用户的动态偏好，在电子商务等领域取得较好推荐效果。然而，鲜见有关EBSN中的面向群组的下一个（Next）事件推荐研究。主要研究面向群组的Next事件推荐策略，但由于群组偏好会发生动态变化，且事件生命周期短、新事件冷启动等问题使得针对群组进行Next事件推荐变得更加困难。首先，针对群组偏好会随时间发生动态变化的特征，将群组与事件的历史交互划分为多个时段。考虑到划分后群组成员数据变得更加稀疏，不利于群组偏好建模，采用基于参与度的排序策略提取当前时段核心成员的成员偏好，并利用注意力机制融合出群组静态偏好。然后，通过序列模型将各个时段的静态偏好融合得到群组动态偏好。最后，将事件推荐视为多标签分类问题，即将上下文看作事件的多个标签，通过预测各个上下文的概率分布以匹配事件，从而有效缓解新事件冷启动问题。实验结果表明，所提出的推荐策略具有较好的性能。

关键词: 基于事件社会网络（EBSN）, 下一个事件推荐, 群组推荐, 注意力机制, 多标签分类

LIAO Guoqiong, YANG Lechuan, WAN Changxuan, LIU Dexi, LIU Xiping. Attention-aware Next Event Recommendation Strategy for Groups[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(2): 499-510.

廖国琼, 杨乐川, 万常选, 刘德喜, 刘喜平. 注意力感知的群组Next事件推荐策略[J]. 计算机科学与探索, 2023, 17(2): 499-510.

References

[1] CHIN A, TIAN J, HAN J, et al. A study of offline events and its influence on online social connections in Douban[C]//Proceedings of the 9th IEEE International Conference on Green Computing and Communications, Beijing, Aug 20-23, 2013. Piscataway: IEEE, 2013: 1021-1028.
[2] RICKEN S, BARKHUUS L, JONES Q. Going online to meet offline: organizational practices of social activities through Meetup[C]//Proceedings of the 8th International Conference on Communities and Technologies, Troyes, Jun 26-30, 2017. New York: ACM, 2017: 139-148.
[3] LIU X, HE Q, TIAN Y, et al. Event-based social networks: linking the online and offline social worlds[C]//Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Beijing, Aug 12-16, 2012. New York: ACM, 2012: 1032-1040.
[4] STRATIGI M, NUMMENMAA J, PITOURA E, et al. Fair sequential group recommendations[C]//Proceedings of the 35th Annual ACM Symposium on Applied Computing, Brno, Mar 30-Apr 3, 2020. New York: ACM, 2020: 1443-1452.
[5] WANG W, ZHANG W, RAO J, et al. Group-aware long-and short-term graph representation learning for sequential group recommendation[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2020: 1449-1458.
[6] SCHEIN A, POPESCUL A, UNGAR L, et al. Methods and metrics for cold-start recommendations[C]//Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Tam-pere, Aug 11-15, 2002. New York: ACM, 2002: 253-260.
[7] LIANG Y, HUANG C L, BAO X G. Sequential dynamic event recommendation in event-based social networks: an upper confidence bound approach[J]. Information Sciences, 2021(1): 1-23.
[8] DU Y, MENG X, ZHANG Y, et al. GERF: a group event recommendation framework based on learning-to-rank[J]. IEEE Transactions on Knowledge and Data Engineering, 2020, 32(4): 674-687.
[9] CUI Q, WU S, HUANG Y, et al. A hierarchical contextual attention-based network for sequential recommendation[J]. Neurocomputing, 2019, 358: 141-149.
[10] 张玉洁, 杜雨露, 孟祥武. 组推荐系统及其应用研究[J]. 计算机学报, 2016, 39(4): 745-764.
ZHANG Y J, DU Y L, MENG X W. Research on group recommender systems and their applications[J]. Chinese Journal of Computers, 2016, 39(4): 745-764.
[11] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, Dec 4-9, 2017. Red Hook: Curran Associates, 2017: 6000-6010.
[12] CAO D, HE X, MIAO L, et al. Attentive group recomm-endation[C]//Proceedings of the 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, Ann Arbor, Jul 8-12, 2018. New York: ACM, 2018: 645-654.
[13] HUANG Z, XU X, ZHU H, et al. An efficient group recom-mendation model with multiattention-based neural networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2020, 31(11): 4461-4474.
[14] MIGLIORINI S, QUINTARELLI E, CARRA D, et al. Sequ-ences of recommendations for dynamic groups: what is the role of context?[C]//Proceedings of the 8th IEEE International Congress on Big Data, Milan, Jul 8-13, 2019. Piscataway: IEEE, 2019: 121-128.
[15] JEONG H J, KIM M H. HGGC: a hybrid group recomm-endation model considering group cohesion[J]. Expert Systems with Applications, 2019, 136: 73-82.
[16] WANG S, HU L, WANG Y, et al. Sequential recommender systems: challenges, progress and prospects[C]//Proceedings of the 28th International Joint Conference on Artificial Inte-lligence, Macao, China, Aug 10-16, 2019. San Francisco: Morgan Kaufmann, 2019: 6332-6338.
[17] RENDLE S, FREUDENTHALER C, SCHMIDT-THIEME L. Factorizing personalized Markov chains for next-basket recom-mendation[C]//Proceedings of the 19th International Conf-erence on World Wide Web, Raleigh,Apr 26-30, 2010. New York: ACM, 2010: 811-820.
[18] TIM D, BENEDIKT L, JüRGEN Z. Sequential user-based recurrent neural network recommendations[C]//Proceedings of the 11th ACM Conference on Recommender Systems, Como, Aug 27-31, 2017. New York: ACM, 2017: 152-160.
[19] KANG W, MCAULEY J. Self-attentive sequential recom-mendation[C]//Proceedings of the 18th IEEE International Conference on Data Mining, Singapore, Nov 17-20, 2018. Washington: IEEE Computer Society, 2018: 197-206.
[20] SUN F, LIU J, WU J, et al. BERT4Rec: sequential recomm-endation with bidirectional encoder representations from transformer[C]//Proceedings of the 28th ACM International Conference on Information and Knowledge Management, Beijing, Nov 3-7, 2019. New York: ACM, 2019: 1441-1450.
[21] ZHANG M, ZHOU Z. A review on multi-label learning algorithms[J]. IEEE Transactions on Knowledge and Data Engineering, 2014, 26(8): 1819-1837.
[22] ZHANG D, ZHAO S, DUAN Z, et al. A multi-label class-ification method using a hierarchical and transparent representation for paper-reviewer recommendation[J]. ACM Transactions on Information Systems, 2020, 38(1): 1-20.
[23] KATARYA R, GAUTAM D. Survey on opinion leader in social network using data mining[C]//Proceedings of the 5th International Conference on Advanced Computing & Communication Systems, Coimbatore, Mar 15-16, 2019. Pisc-ataway: IEEE, 2019: 506-509.
[24] 许晓明, 梅红岩, 于恒, 等. 基于偏好融合的群组推荐方法研究综述[J]. 小型微型计算机系统, 2020, 41(12): 2500-2508.
XU X M, MEI H Y, YU H, et al. Review of group recom-mendation methods based on preference fusion[J]. Journal of Chinese Computer Systems, 2020, 41(12): 2500-2508.
[25] TRINH T, WU D, WANG R, et al. An effective content-based event recommendation model[J]. Multimedia Tools and Applications, 2021, 80(11): 16599-16618.
[26] FENG S, LI X, ZENG Y, et al. Personalized ranking metric embedding for next new POI recommendation[C]//Proce-edings of the 24th International Joint Conferences on Arti-ficial Intelligence, Buenos Aires, Jul 25-31, 2015. Menlo Park: AAAI, 2015: 2069-2075.
[27] SEO Y, KIM Y, LEE E, et al. An enhanced aggregation method considering deviations for a group recommendation[J]. Expert Systems with Applications, 2018, 93: 299-312.
[28] WANG Y, TANG J. Event2Vec: learning event representations using spatial-temporal information for recommendation[C]//LNCS 11441: Proceedings of the 23rd Pacific-Asia Confe-rence on Knowledge Discovery and Data Mining, Macau, China, Apr 14-17, 2019. Cham: Springer, 2019: 314-326.
廖国琼（1969—），男，湖北黄石人，教授，博士生导师，CCF高级会员，主要研究方向为数据库、数据挖掘、推荐系统。
LIAO Guoqiong, born in 1969, professor, Ph.D. supervisor, senior member of CCF. His research interests include databases, data mining and recommendation systems.
杨乐川（1996—），男，江西南昌人，硕士研究生，主要研究方向为推荐系统。
YANG Lechuan, born in 1996, M.S. candidate. His research interest is recommendation systems.