Modeling sentimental bias and temporal dynamics for adaptive deep recommendation system

作者：

Highlights：

• The proposed method addresses the unbalanced and data sparsity problems.

• Sentiment bias and temporal dynamics are explored to improve recommendation quality.

• We design a deep learning method based on long- and short-term user preferences.

• The performance of the proposed models is evaluated on several Amazon datasets.

摘要

•The proposed method addresses the unbalanced and data sparsity problems.•Sentiment bias and temporal dynamics are explored to improve recommendation quality.•We design a deep learning method based on long- and short-term user preferences.•The performance of the proposed models is evaluated on several Amazon datasets.

论文关键词：Sentiment bias,Temporal dynamics,Long-short-term memory,Recommender system

论文评审过程：Received 24 May 2021, Revised 23 September 2021, Accepted 18 November 2021, Available online 28 November 2021, Version of Record 4 December 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.116262