基于方向性偏好的个性化序列推荐模型
Personalized Sequence Recommendation Model Based on Directional Preference

DOI: 10.12677/CSA.2021.1112297, PP. 2932-2944

Keywords: 序列推荐，偏好方向，胶囊网络，多头自注意力机制，短期需求
Sequence Recommendation, Preference Direction, Capsule Network, Multi-Head Self-Attention, Short-Term Demand

Full-Text   Cite this paper   Add to My Lib

Abstract:

目前推荐系统主要基于用户偏好和物品的相似度等标量进行推荐，忽略了用户的偏好方向，增加了不相关推荐的风险。基于此，本文提出基于方向性偏好的个性化序列推荐模型，通过推荐符合用户偏好方向的物品，综合用户的偏好和需求进行推荐从而提高了推荐的准确性。本文以电影评论数据集为背景，使用选择器多头自注意力机制和改进胶囊网络分别提取用户的长期偏好和短期需求，然后根据用户长期偏好和短期需求构成的偏好向量进行推荐。实验结果表明，模型的推荐准确性指标相比原模型提升了52%。
The current recommendation system is mainly based on scalar variables such as similarity of user preferences and items, ignoring the user’s preference direction, and increasing the risk of irrelevant recommendations. Based on this, this paper proposes a personalized sequence recommendation model based on directional preference, which improves the accuracy of recommendation by recommending items that conform to the user’s preference direction and integrating the user’s preferences and needs. Based on the movie review data set, this paper uses the selector multi-head self-attention mechanism and the capsule network to extract the user’s long-term preferences and short-term needs, and then recommends based on the user’s long-term preferences and short-term needs. The experimental results show that the recommended accuracy index of the model is improved by 52% compared with the original model.

References

[1]	马宏伟, 张光卫, 李鹏. 协同过滤推荐算法综述[J]. 小型微型计算机系统, 2009, 30(7): 1282-1288.
[2]	Folajimi, Y. and Olowofoyeku, K. (2014) Web Items Recommendation Using Hybridized Content-Based and Collaborative Filtering Techniques. Jour-nal of Computer Science and Its Application, 21, 64-72.
[3]	Liang, Z., Peng, L.-F. and Phelan, C.A. (2014) Novel Recommendation of User-Based Collaborative Filtering. Journal of Digital Information Management, 12, 165-175.
[4]	Zhou, T.-X., Jiang, Z.-B., Liu, X.-J., et al. (2020) Research on the Long-Term and Short-Term Forecasts of Navigable River’s Water-Level Fluctuation Based on the Adaptive Multilayer Perceptron. Journal of Hydrology, 591, Article ID: 125285. https://doi.org/10.1016/j.jhydrol.2020.125285
[5]	周飞燕, 金林鹏, 董军. 卷积神经网络研究综述[J]. 计算机学报, 2017, 40(6): 1229-1251.
[6]	Yuan, W.-H., Hong, W., Yu, X.-M., et al. (2020) Attention-Based Context-Aware Sequential Recommenda-tion Model. Information Sciences, 510, 122-134. https://doi.org/10.1016/j.ins.2019.09.007
[7]	宗春梅, 张月琴, 赵青杉. 等. 可视化支持下CNN在个性化推荐算法中的应用[J]. 计算机系统应用, 2020, 29(6): 204-210.
[8]	Wafa, S. and Byun, Y.C. (2020) A Context-Aware Location Recommendation System for Tourists Using Hierarchical LSTM Model. Sustainability, 12, Article No. 4107. https://doi.org/10.3390/su12104107
[9]	沈学利, 杜志伟. 融合自注意力机制与长短期偏好的序列推荐模型[J]. 计算机应用研究, 2020, 38(5): 1371-1375+1380.
[10]	Wang, S.-J., Hu, L. and Wang, Y. (2019) Sequential Recommender Systems: Challenges, Progress and Prospects. Proceedings of the 28th International Joint Conference on Artificial Intelligence, Macao (China), 10-16 August 2019, 6332-6338. https://doi.org/10.24963/ijcai.2019/883
[11]	Wu, C.-Y., Amr, A., Alex, B., Smola, A.J. and Jing, H. (2017) Recurrent Recommender Networks. Proceedings of the 10th ACM International Conference on Web Search and Data Mining, Cambridge, 6-10 February 2017, 495-503. https://doi.org/10.1145/3018661.3018689
[12]	Yang, Y., Jang, H.J. and Kim, B. (2020) A Hybrid Recommender System for Sequential Recommendation: Combining Similarity Models with Markov Chains. IEEE Access, 8, 190136-190146. https://doi.org/10.1109/ACCESS.2020.3027380
[13]	夏瑜潞. 循环神经网络的发展综述[J]. 电脑知识与技术, 2019, 15(21): 182-184.
[14]	Tang, J.-X., Belletti, F., Jain, S., et al. (2019) Towards Neural Mixture Recommender for Long Range Dependent User Sequences. Proceedings of the World Wide Web Conference, San Francisco, May 2019, 1782-1793. https://doi.org/10.1145/3308558.3313650
[15]	Li, X.-Q., Jiang, W.-J., Chen, W.G., et al. (2019) HAES: A New Hybrid Ap-proach for Movie Recommendation with Elastic Serendipity. Proceedings of the 28th ACM International Conference, Beijing, Novem-ber 2019, 1503-1512. https://doi.org/10.1145/3357384.3357868
[16]	Li, X.-Q., Jiang, W.-J., Chen, W.-G., et al. (2020) Directional and Explainable Serendipity Recommendation. Proceedings of the Web Conference, Taipei, April 2020, 122-132. https://doi.org/10.1145/3366423.3380100
[17]	Hinton, G.E. (2017) Dynamic Routing between Capsules. 31st Conference on Neural Information Processing Systems, Long Beach, 4-9 December 2017, 1-11.

Full-Text