分层级描述感知的个性化推荐系统

doi:10.3969/j.issn.1000-5641.2023.06.007

摘要/Abstract

摘要：

评论文本蕴含丰富的用户信息和物品信息, 对于用户的购买决策有着重要作用. 当用户面对不同的目标物品时, 会展现复杂的兴趣. 因此准确提取评论中的语义特征并建模物品和用户之间的上下文交互, 对学习用户偏好和物品属性十分关键. 专注于增强推荐系统的个性化捕捉和动态兴趣建模能力, 考虑不同特征的有用性, 提出了一种分层级描述感知的个性化推荐 (description-aware personal recommendation, DAPR) 算法: 在评论集合的单词层级, 设计个性化的信息选择网络, 提取重要的单词语义特征; 在评论层级, 基于交叉注意力机制设计神经网络, 动态地学习评论的有用性; 拼接评论摘要作为描述, 设计协同注意力网络, 捕捉更丰富的上下文感知的特征. 在5个Amazon数据集上的实验结果证明了所提方法能取得与基线模型相当的推荐性能.

关键词: 推荐系统, 基于评论, 注意力机制, 协同注意力

Abstract:

Review text contains comprehensive user and item information and it has a great influence on users’ purchase decision. When users interact with different target items, they may show complex interests. Therefore, accurately extracting review semantic features and modeling the contextual interaction between items and users is critical for learning user preferences and item attributes. Focusing on enhancing the personalization capture and dynamic interest modeling abilities of recommender systems, and considering the usefulness of different features, we propose a hierarchical description-aware personalized recommendation (DAPR) algorithm. At the word level of review text, we design a personalized information selection network to extract important word semantic features. At the review level, we design a neural network based on a cross-attention mechanism to dynamically learn the usefulness of reviews, concatenate review summaries as descriptions, and devise a co-attention network to capture rich context-aware features. The analysis of five Amazon datasets reveal that the proposed method can achieve comparable recommendation performance to the baseline models.

Key words: recommendation system, review-based, attention mechanism, co-attention

中图分类号:

TP391

陈道佳, 陈志云. 分层级描述感知的个性化推荐系统[J]. 华东师范大学学报（自然科学版）, 2023, 2023(6): 73-84.

Daojia CHEN, Zhiyun CHEN. Hierarchical description-aware personalized recommendation system[J]. Journal of East China Normal University(Natural Science), 2023, 2023(6): 73-84.

图/表 5

图1

表1

表2

表3

表4

参考文献 29

1	MCAULEY J, LESKOVEC J. Hidden factors and hidden topics: Understanding rating dimensions with review text [C]// Proceedings of the 7th ACM Conference on Recommender Systems. ACM, 2013: 165-172.
2	LING G, LYU M R, KING I. Ratings meet reviews, a combined approach to recommend [C]// Proceedings of the 8th ACM Conference on Recommender Systems. ACM, 2014: 105-112.
3	ZHENG L, NOROOZI V, YU P S. Joint deep modeling of users and items using reviews for recommendation [C]// Proceedings of the 10th ACM International Conference on Web Search and Data Mining. ACM, 2017: 425-434.
4	SEO S, HUANG J, YANG H, et al. Interpretable convolutional neural networks with dual local and global attention for review rating prediction [C]// Proceedings of the 11th ACM Conference on Recommender Systems. ACM, 2017: 297-305.
5	CHEN C, ZHANG M, LIU Y Q, et al. Neural attentional rating regression with review-level explanations [C]// Proceedings of the 2018 World Wide Web Conference. ACM, 2018: 1583-1592.
6	LIU D H, LI J, DU B, et al. DAML: Dual attention mutual learning between ratings and reviews for item recommendation [C]// Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2019: 344-352.
7	WU L B, QUAN C, LI C L, et al. A context-aware user-item representation learning for item recommendation[J]. ACM Transactions on Information Systems, 2019, 37(2). DOI: 10.1145/3298988.
8	CHIN J Y, ZHAO K Q, JOTY S, et al. ANR: Aspect-based neural recommender [C]// Proceedings of the 27th ACM International Conference on Information and Knowledge Management. ACM, 2018: 147-156.
9	WU S W, ZHANG Y X, ZHANG W T, et al. Enhanced review-based rating prediction by exploiting aside information and user influence [J]. Knowledge-Based Systems, 2021, 222: 107015.
10	TAY Y, LUU A T, HUI S C. Multi-pointer co-attention networks for recommendation [C]// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2018: 2309-2318.
11	WU C H, WU F Z, LIU J X, et al. Hierarchical user and item representation with three-tier attention for recommendation [C]// Proceedings of NAACL-HLT 2019. Association for Computational Linguistics (ACL), 2019: 1818-1826.
12	ZENG H S, AI Q Y. A hierarchical self-attentive convolution network for review modeling in recommendation systems [EB/OL]. (2020-11-26)[2022-03-21]. https://doi.org/10.48550/arXiv.2011.13436.
13	KOREN Y, BELL R, VOLINSKY C.. Matrix factorization techniques for recommender systems. Computer, 2009, 42 (8): 30- 37.
14	TAN Y Z, ZHANG M, LIU Y Q, et al. Rating-boosted latent topics: Understanding users and items with ratings and reviews [C]// Proceedings of the 25th International Joint Conference on Artificial Intelligence (IJCAI-16). IJCAI, 2016: 2640-2646.
15	BAO Y, FANG H, ZHANG J.. TopicMF: Simultaneously exploiting ratings and reviews for recommendation. Proceedings of the AAAI Conference on Artificial Intelligence, 2014, 28 (1): 2- 8. doi: 10.1609/aaai.v28i1.8715
16	DIAO Q M, QIU M H, WU C Y, et al. Jointly modeling aspects, ratings and sentiments for movie recommendation (JMARS) [C]// Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2014: 193-202.
17	WANG H, WANG N Y, YEUNG D Y. Collaborative deep learning for recommender systems [C]// Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2015: 1235-1244.
18	KIM D, PARK C, OH J, et al. Convolutional matrix factorization for document context-aware recommendation [C]// Proceedings of the 10th ACM Conference on Recommender Systems. ACM, 2016: 233-240.
19	CATHERINE R, COHEN W. TransNets: Learning to transform for recommendation [C]// Proceedings of the 11th ACM Conference on Recommender Systems. ACM, 2017: 288-296.
20	WANG X, OUNIS I, MACDONALD C. Leveraging review properties for effective recommendation [C]// Proceedings of the Web Conference 2021. ACM, 2021: 2209-2219.
21	DONG X, NI J C, CHENG W, et al. Asymmetrical hierarchical networks with attentive interactions for interpretable review-based recommendation [C]// Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI-20). AAAI, 2020: 7667-7674.
22	LI C L, QUAN C, PENG L, et al. A capsule network for recommendation and explaining what you like and dislike [C]// Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 2019: 275-284.
23	LIU H T, WANG W J, PENG Q Y, et al. Toward comprehensive user and item representations via three-tier attention network [J]. ACM Transactions on Information Systems, 2021, 39(3). DOI: 10.1145/3446341.
24	GAO J Y, LIN Y, WANG Y S, et al. Set-sequence-graph: A multi-view approach towards exploiting reviews for recommendation [C]// Proceedings of the 29th ACM International Conference on Information and Knowledge Management. ACM, 2020: 395-404.
25	CHEN Y. Convolutional neural network for sentence classification [D]. Waterloo, ON Canada: University of Waterloo, 2015.
26	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. ACM, 2017: 6000–6010.
27	DAUPHIN Y N, FAN A, AULI M, et al. Language modeling with gated convolutional networks [C]// Proceedings of the 34th International Conference on Machine Learning - Volume 70. ACM, 2017: 933-941.
28	OVED N, LEVY R. Pass: Perturb-and-select summarizer for product reviews [C]// Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. Association for Computational Linguistics (ACL), 2021: 351-365.
29	LU J S, YANG J W, BATRA D, et al. Hierarchical question-image co-attention for visual question answering [C]// Proceedings of the 30th International Conference on Neural Information Processing Systems. ACM, 2016: 289-297.

数据集	评论数 (用户)/条	评论数 (物品)/条	评论长度	用户数量/个	物品数量/个	总评论数/条	评分密度/%
Digital Music	8	14	164	5541	3568	64706	0.327
Office Product	9	16	111	4905	2420	53258	0.449
Grocery and Food	8	10	78	14681	8713	151254	0.118
Toys and Games	7	11	77	19412	11924	167597	0.072
Video Games	7	15	147	24303	10672	231780	0.089

模型			MSE
模型	Digital Misic	Office Product	Grocery and Food	Toys and Games	Video Games
MF	0.8707	0.7149	1.0403	0.8808	1.2930
DeepCoNN	0.8109	0.7128	1.0223	0.8335	1.1950
D-Attn	0.8305	0.7103	1.0092	0.8334	1.2197
NARRE	0.8098	0.7064	0.9832	0.8025	1.1422
DAML	0.8102	0.7086	0.9836	0.8143	1.1722
MPCN	1.1192	0.8304	1.1549	0.9281	1.2610
DAPR-gate	0.8026	0.7059	0.9881	0.8055	1.1347
DAPR	0.7956	0.6956	0.9804	0.7967	1.1249

模型		MSE
模型	Digital Music	Toys and Games	Video Games
Base	0.8008	0.8144	1.1520
Base + Avg	0.8010	0.8162	1.1532
DAPR-WA	0.8095	0.8185	1.1467
DAPR-RA	0.7930	0.7998	1.1305
DAPR-Co	0.8124	0.8198	1.1424
DAPR	0.7956	0.7967	1.1249

模型		MSE
模型	Digital Music	Toys and Games	Video Games
DAPR-Dot	0.8236	0.8358	1.1625
DAPR-FM	0.8112	0.8100	1.1205
DAPR-LFM	0.7956	0.7967	1.1249

[1]	王畅, 马丹, 许华容, 陈攀峰, 陈梅, 李晖. SA-MGKT: 基于自注意力融合的多图知识追踪方法[J]. 华东师范大学学报（自然科学版）, 2024, 2024(5): 20-31.
[2]	刘家伟, 林欣. 基于解耦常识性关联的图像描述生成算法[J]. 华东师范大学学报（自然科学版）, 2024, 2024(2): 131-142.
[3]	冯路平, 施力业, 吴雯, 郑骏, 胡文心, 郑巍. 基于偏好级别陌生人信息辅助的推荐系统[J]. 华东师范大学学报（自然科学版）, 2024, 2024(2): 53-64.
[4]	姜璐璐, 孙司琦, 邹海东, 陆丽娜, 冯瑞. 基于双视图特征融合的糖尿病视网膜病变分级[J]. 华东师范大学学报（自然科学版）, 2023, 2023(6): 39-48.
[5]	段志尚, 冉懿, 吕笃良, 祁杰, 钟佳晨, 袁培森. 基于残差网络和深度可分离卷积增强自注意力机制的窃电识别[J]. 华东师范大学学报（自然科学版）, 2023, 2023(5): 193-204.
[6]	葛进, 陆雪松. 基于UI图像的Web前端代码自动生成[J]. 华东师范大学学报（自然科学版）, 2023, 2023(5): 100-109.
[7]	武朝阳, 毛嘉莉. 基于神经网络的行驶时长预测[J]. 华东师范大学学报（自然科学版）, 2023, 2023(2): 106-118.
[8]	童根梅, 朱敏. 基于双向长短记忆网络和门控注意力的文本分类网络[J]. 华东师范大学学报（自然科学版）, 2022, 2022(2): 67-75.
[9]	梁艳春, 房爱莲. 基于多通道卷积神经网络的中文文本关系抽取[J]. 华东师范大学学报（自然科学版）, 2021, 2021(3): 96-104.
[10]	李小昌, 陈贝, 董启文, 陆雪松. 基于自编码器的旅行同伴挖掘[J]. 华东师范大学学报（自然科学版）, 2020, 2020(5): 179-188.
[11]	朱思涵, 浦剑. 基于序列特征的点击率预测模型[J]. 华东师范大学学报（自然科学版）, 2020, 2020(4): 134-146.
[12]	傅裕, 李优, 林煜明, 周娅. 基于自注意力机制的冗长商品名称精简方法[J]. 华东师范大学学报(自然科学版), 2019, 2019(5): 113-122,167.
[13]	杨东明, 杨大为, 顾航, 洪道诚, 高明, 王晔. 面向初等数学的知识点关系提取研究[J]. 华东师范大学学报(自然科学版), 2019, 2019(5): 53-65.
[14]	王凯, 李博涵, 万朔, 张安曼, 关东海. 基于反向最远邻的商品推荐算法研究[J]. 华东师范大学学报(自然科学版), 2019, 2019(3): 63-77.
[15]	张巍, 郑骏, 逄娇娜, 白玥. 基于自相似矩阵的协同过滤推荐算法[J]. 华东师范大学学报(自然科学版), 2018, 2018(4): 120-128,146.