梁顺攀^{1, 2,,},
刘伟¹,
尤殿龙^{1, 2},
刘泽谦¹,
张付志^{1, 2}
1.燕山大学信息科学与工程学院 秦皇岛 066004
2.燕山大学河北省软件工程重点实验室 秦皇岛 066004
基金项目:国家自然科学基金(62072393)， 河北省自然科学基金(G2021203010，F2021203038)

详细信息

作者简介:梁顺攀：男，1976年生，副教授，研究方向为推荐系统
刘伟：男，1996年生，硕士生，研究方向为推荐系统
尤殿龙：男，1981年生，副教授，研究方向为特征选择
刘泽谦：男，1996年生，硕士生，研究方向为推荐系统
张付志：男，1964年生，教授，研究方向为推荐系统

通讯作者:梁顺攀　liangshunpan@ysu.edu.cn

中图分类号:TP391

计量

文章访问数:43
HTML全文浏览量:25
PDF下载量:18
被引次数:0

出版历程

收稿日期:2020-11-02
修回日期:2021-10-25
网络出版日期:2021-11-10
刊出日期:2021-12-21

Self-attention Capsule Network Rate Prediction with Review Quality

Shunpan LIANG^{1, 2,,},
Wei LIU¹,
Dianlong YOU^{1, 2},
Zeqian LIU¹,
Fuzhi ZHANG^{1, 2}
1. College of Information Science and Engineering, Yanshan University, Qinhuangdao 066004, China
2. Key Laboratory for Software Engineering of Hebei Province, Yanshan University, Qinhuangdao 066004, China
Funds:The National Natural Science Foundation of China (62072393), The Natural Science Foundation of Hebei Province (G2021203010, F2021203038)


摘要
摘要:基于评论文档的推荐系统普遍采用卷积神经网络识别评论的语义，但由于卷积神经网络存在“不变性”，即只关注特征是否存在，忽略特征的细节，卷积中的池化操作也会丢失文本中的一些重要信息；另外，使用用户项目交互的全部评论文档作为辅助信息不仅不会提升语义的质量，反而会受到其中低质量评论的影响，导致推荐结果并不准确。针对上述提到的两个问题，该文提出了自注意力胶囊网络评分预测模型(Self-Attention Capsule network Rate prediction, SACR)，模型使用可以保留特征细节的自注意力胶囊网络挖掘评论文档，使用用户和项目的编号信息标记低质量评论，并且将二者的表示相融合用以预测评分。该文还改进了胶囊的挤压函数，从而得到更精确的高层胶囊。实验结果表明，SACR在预测准确性上较一些经典模型及最新模型均有显著的提升。
关键词:推荐系统/
胶囊网络/
注意力/
评论质量/
评分预测
Abstract:Recommendation systems based on reviews generally use convolutional neural networks to identify the semantics. However, due to the “invariance” of convolutional neural networks, that is, they only pay attention to the existence of features and ignore the details of features. The pooling operation will also lose some important information; In addition, using all the reviews as auxiliary information will not only not improve the quality of semantics, but will be affected by the low-quality reviews, this will lead to inaccurate recommendations. In order to solve the two problems mentioned above, this paper proposes a SACR (Self-Attention Capsule network Rate prediction) model. SACR uses a self-attention capsule network that can retain feature details to mine reviews, uses user and item ID to mark low-quality reviews, and merge the two representations to predict the rate. This paper also improves the squeeze function of the capsule, which can obtain more accurate high-level capsules. The experiments show that SACR has a significant improvement in prediction accuracy compared to some classic models and the latest models.
Key words:Recommendation system/
Capsule network/
Attention/
Review quality/
Rate prediction



PDF全文下载地址:

https://jeit.ac.cn/article/exportPdf?id=c6aa45ed-2f42-4812-bf0b-c5a5979c0d1e