基于物品描述和评论的多粒度注意力机制的推荐
Multi-Granularity Attention Mechanism for Recommendation Systems Based on Item Descriptions and Reviews
摘要: 本研究针对传统推荐系统依赖评分信息、面临数据稀疏性的局限，以及深度学习模型的可解释性不足，提出了一种融合评分数据和文本信息(评论、物品描述)的多粒度注意力机制的推荐模型(Multi-Grained Attention Recommendation, MGAR)。本文采用两个并行的卷积神经网络(CNN)分别处理用户和物品的评论与描述，并通过词级、短语级和句子级的注意力机制来提取不同层次的语义信息，实现评论文本的深度融合，从而更有效地捕捉用户偏好和物品特性。在Amazon上的4个子数据集的实验结果表明，本文提出的模型在预测准确度上均优于传统的基于评分的推荐模型和近年来流行的DeepCoNN模型。
Abstract: This study addresses the challenges faced by traditional recommendation systems that rely on rating information and contend with data sparsity, as well as the lack of interpretability in deep learning models. It proposes a Multi-Grained Attention Recommendation (MGAR) model that integrates rating data with textual information (reviews, product descriptions). Utilizing two parallel Convolutional Neural Networks (CNNs) to process user and item reviews and descriptions, the model employs word-level, phrase-level, and sentence-level attention mechanisms to extract semantic information across various granularities. This facilitates a deep integration of review text, enabling a more effective capture of user preferences and product characteristics. Experimental results on four Amazon datasets indicate that the proposed model outperforms traditional rating-based recommendation systems and the recently popular DeepCoNN model in terms of predictive accuracy.
文章引用：刘世新. 基于物品描述和评论的多粒度注意力机制的推荐[J]. 建模与仿真, 2024, 13(3): 2429-2440. https://doi.org/10.12677/mos.2024.133222

参考文献

[1] Anyosa, S.C., Vinagre, J. and Jorge, A.M. (2018) Incremental Matrix Co-Factorization for Recommender Systems with Implicit Feedback. Companion Proceedings of the Web Conference 2018, Lyon, 23-27 April 2018, 1413-1418. [Google Scholar] [CrossRef] 
[2] Messaoudi, F. and Loukili, M. (2024) E-Commerce Personalized Recommendations: A Deep Neural Collaborative Filtering Approach. Operations Research Forum, 5, Article No. 5. [Google Scholar] [CrossRef] 
[3] Grbovic, M., Radosavljevic, V., Djuric, N., et al. (2015) E-Commerce in Your Inbox: Product Recommendations at Scale. Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Sydney, 10-13 August 2015, 1809-1818. [Google Scholar] [CrossRef] 
[4] Chen, H., Li, Z., Wang, Z., et al. (2021) Edge Data Based Trailer Inception Probabilistic Matrix Factorization for Contextaware Movie Recommendation. World Wide Web, 25, 1863-1882. [Google Scholar] [CrossRef] 
[5] Li, Z., Chen, H., Lin, K., Shakhov, V., Shi, L. and Yu, J. (2021) From Edge Data to Recommendation: A Double Attention-Based Deformable Convolutional Network. Peer-to-Peer Networking and Applications, 14, 3984-3997. [Google Scholar] [CrossRef] 
[6] Bosri, R., Rahman, M.S., Bhuiyan, M.Z.A. and Omar, A.A. (2021) Integrating Blockchain with Artificial Intelligence for Privacy-Preserving Recommender Systems. IEEE Transactions on Network Science and Engineering, 8, 1009-1018. [Google Scholar] [CrossRef] 
[7] Wang, X., Wang, R., Shi, C., Song, G. and Li, Q. (2020) Multi-Component Graph Convolutional Collaborative Filtering. Proceedings of the AAAI Conference on Artificial Intelligence, 34, 6267-6274. [Google Scholar] [CrossRef] 
[8] Wang, C. and Blei, D.M. (2011) Collaborative Topic Modeling for Recommending Scientific Articles. Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Diego, 21-24 August 2011, 448-456. [Google Scholar] [CrossRef] 
[9] Ling, G.L., Yu, M.R. and King, I. (2014) Ratings Meet Reviews, a Combined Approach to Recommend. Proceedings of the 8th ACM Conference on Recommender systems, Foster City, 6-10 October 2014, 105-112. [Google Scholar] [CrossRef] 
[10] Zheng, L., Noroozi, V. and Yu, P.S. (2017) Joint Deep Modeling of Users and Items Using Reviews for Recommendation. Proceedings of the Tenth ACM International Conference on Web Search and Data Mining, Cambridge, 6-10 February 2017, 425-434. [Google Scholar] [CrossRef] 
[11] Seo, S., Huang, J., Yang, H. and Liu, Y. (2017) Interpretable Convolutional Neural Networks with Dual Local and Global Attention for Review Rating Prediction. Proceedings of the Eleventh ACM Conference on Recommender Systems, Como, 27-31 August 2017, 297-305. [Google Scholar] [CrossRef] 
[12] Wu, L., Quan, C., Li, C., et al. (2019) A Context-Aware User-Item Representation Learning for Item Recommendation. ACM Transactions on Information Systems, 37, Article No. 22. [Google Scholar] [CrossRef] 
[13] Chen, C., Zhang, M., Liu, Y., et al. (2018) Neural Attentional Rating Regression with Review-Level Explanations. Procedings of the 2018 World Wide Web Conference, Lyon, 23-27 April 2018, 1583-1592. [Google Scholar] [CrossRef] 
[14] Tay, Y., Luu, A.T. and Hui, S.C. (2018) Multi-Pointer Co-Attention Networks for Recommendation. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, London, 19-23 August 2018, 2309-2318. [Google Scholar] [CrossRef] 
[15] Zhen, L., Yuan, B. and Ma, Y. (2022) A Multi-Task Dual Attention Deep Recommendation Model Using Ratings and Review Helpfulness. Applied Intelligence, 52, 5595-5607. [Google Scholar] [CrossRef] 
[16] Li, Z., Chen, H., Ni, Z., et al. (2022) ARPCNN: Auxiliary Review-Based Personalized Attentional CNN for Trustworthy Recommendation. IEEE Transactions on Industrial Informatics, 19, 1018-1029. [Google Scholar] [CrossRef] 
[17] Dezfouli, P.A.B., Momtazi, S. and Dehghan, M. (2021) Deep Neural Review Text Interaction for Recommendation Systems. Applied Soft Computing, 100, Article ID: 106985. [Google Scholar] [CrossRef] 
[18] Donghyun, K., Park, C., Oh, J., et al. (2016) Convolutional Matrix Factorization for Document Context-Aware Recommendation. Proceedings of the 10th ACM Conference on Recommender Systems, Boston, 15-19 September 2016, 233-240. [Google Scholar] [CrossRef] 
[19] Chen, J., Zhang, H., He, X., et al. (2017) Attentive Collaborative Filtering: Multimedia Recommendation with Item-and Component-Level Attention. Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, Shinjuku, 7-11 August 2017, 335-344. [Google Scholar] [CrossRef] 
[20] Xiao, J., Ye, H., He, X., et al. (2017) Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks. Proceedings of the 26th International Joint Conference on Artificial Intelligence, Melbourne, 19-25 August 2017, 3119-3125. [Google Scholar] [CrossRef] 
[21] Liu, H., Wu, F., Wang, W., et al. (2019) NRPA: Neural Recommendation with Personalized Attention. Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, Paris, 21-25 July 2019, 1233-1236. [Google Scholar] [CrossRef] 
[22] Mikolov, T., Sutskever, I., Chen, K., Corrado, G. and Dean, J. (2013) Distributed Representations of Words and Phrases and Their Compositionality. Proceedings of the 26th International Conference on Neural Information Processing Systems, Lake Tahoe, 5-10 December 2013, 3111-3119.

为你推荐