摘要
为了捕捉在线购物时用户与商品之间的动态交互关系,提高推荐系统(RS)的准确度,提出了结合用户倾向性和商品吸引力的用户评价预测方法。首先,将评论分为用户评论文本和商品评论文本,分别输入两个交互卷积神经网络(CNN),并结合注意力机制,动态捕捉文本中的语义信息和上下文信息,得到用户和商品的自适应特征;然后,利用交互注意力网络,分析商品特征和用户特征的动态交互关系,计算出用户对特定商品的倾向性和商品对特定用户的吸引力;最后,通过预测模块提供用户对商品的准确评价预测。在数据集上进行实验,结果表明,所提方法取得了最优性能,比其他方法的MAE和RMSE性能分别至少提升了15.1%和13.6%。此外,基于Top-K的统计指标进一步验证了所提方法的商品推荐精准度。
In order to capture the dynamic interaction between users and items during online shopping and improve the accuracy of recommendation systems(RS),a user rating prediction method combining user preference and item attractiveness is proposed.The reviews are divided into user review texts and product review texts, which are fed into two convolutional neural networks(CNN),and combined with an attention mechanism to dynamically capture semantic and contextual information in the texts, and obtain user and item adaptive representations.Subsequently, using the interactive attention network, the dynamic interaction between the item features and the user features is analyzed to calculate the user preference on specific items and the attractiveness of the items to a specific user.Finally, the prediction module is used to provide accurate predictions about user ratings to unseen items.Results on experimental datasets show that the proposed method achieves optimal performance, with at least 15.1% and 13.6% improvement in MAE and RMSE performance compared to other advanced methods.In addition, the statistical metrics based on Top-K further validate the accuracy of the proposed method for product recommendation.
作者
任胜兰
郭慧娟
黄文豪
汤志宏
亓慧
REN Sheng-lan;GUO Hui-juan;HUANG Wen-hao;TANG Zhi-hong;Qi Hui(College of Computer Science and Technology,Taiyuan Normal University,Jinzhong,Shanxi 030619,China;College of Information and Computer,Taiyuan University of Technology,Taiguan 030600,China;School of Software Engineering,South China University of Technology,Guangzhou 510006,China;Information Engineering College,Jiangxi University of Technology,Nanchang 330098,China)
出处
《计算机科学》
CSCD
北大核心
2022年第10期126-131,共6页
Computer Science
基金
山西省自然科学基金(201801D121147)
山西省教育厅项目(2021YJJG269)
山西省科技厅基础研究项目(自由探索)(20210302123334)
江西省教育厅科学技术研究项目(GJJ191016)。
关键词
推荐系统
用户倾向性
卷积神经网络
交互注意力机制
上下文特征
Recommendation system
User preference
Convolutional neural network
Interactive-attention mechanism
Contextual features
