华东师范大学学报(自然科学版) ›› 2023, Vol. 2023 ›› Issue (6): 73-84.doi: 10.3969/j.issn.1000-5641.2023.06.007

• 计算机科学 • 上一篇    下一篇

分层级描述感知的个性化推荐系统

陈道佳1, 陈志云2,*()   

  1. 1. 华东师范大学 计算机科学与技术学院, 上海 200062
    2. 华东师范大学 数据科学与工程学院, 上海 200062
  • 收稿日期:2022-05-04 出版日期:2023-11-25 发布日期:2023-11-23
  • 通讯作者: 陈志云 E-mail:chenzhy@cc.ecnu.edu.cn
  • 基金资助:
    教育部产学研项目(201902146018)

Hierarchical description-aware personalized recommendation system

Daojia CHEN1, Zhiyun CHEN2,*()   

  1. 1. School of Computer Science and Technology, East China Normal University, Shanghai 200062, China
    2. School of Data Science and Engineering, East China Normal University, Shanghai 20062, China
  • Received:2022-05-04 Online:2023-11-25 Published:2023-11-23
  • Contact: Zhiyun CHEN E-mail:chenzhy@cc.ecnu.edu.cn

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: