Learning persona-driven personalized sentimental representation for review-based recommendation

作者：

Highlights：

• A persona-driven sentimental model is proposed for review-based recommendation.

• The usage habits and analogous tones are explored from textual reviews.

• Seq-based and frag-based features are considered to learn sentimental representation.

• Experimental results demonstrate the effectiveness of the proposed PSAR.

摘要

•A persona-driven sentimental model is proposed for review-based recommendation.•The usage habits and analogous tones are explored from textual reviews.•Seq-based and frag-based features are considered to learn sentimental representation.•Experimental results demonstrate the effectiveness of the proposed PSAR.

论文关键词：Review mining,Sentimental representation learning,Attention neural networks,Review-based recommendation

论文评审过程：Received 6 April 2021, Revised 5 April 2022, Accepted 23 April 2022, Available online 2 May 2022, Version of Record 10 May 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117317