REDRL: A review-enhanced Deep Reinforcement Learning model for interactive recommendation

作者：

Highlights：

• Mining information in reviews and interaction data via the pretrained model.

• Modeling long-term dynamic preferences of users accurately and discriminately.

• Filtering irrelevant items and getting candidate items dynamically from a new anger.

• Better interactive recommendation based on deep reinforcement learning.

摘要

•Mining information in reviews and interaction data via the pretrained model.•Modeling long-term dynamic preferences of users accurately and discriminately.•Filtering irrelevant items and getting candidate items dynamically from a new anger.•Better interactive recommendation based on deep reinforcement learning.

论文关键词：Recommender system,Deep reinforcement learning,Review analysis

论文评审过程：Received 9 July 2022, Revised 12 September 2022, Accepted 25 September 2022, Available online 4 October 2022, Version of Record 12 October 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118926