A deceptive review detection framework: Combination of coarse and fine-grained features

作者：

Highlights：

• Propose a novel framework that combines both coarse and fine-grained features.

• Extract the topic-based semantic features as the coarse-grained features.

• Extract the implicit word vectors features as the fine-grained features.

• Appropriate to be applied in real-life mixed unbalanced e-commerce environments.

摘要

•Propose a novel framework that combines both coarse and fine-grained features.•Extract the topic-based semantic features as the coarse-grained features.•Extract the implicit word vectors features as the fine-grained features.•Appropriate to be applied in real-life mixed unbalanced e-commerce environments.

论文关键词：Deceptive reviews detection,LDA topic model,Deep learning,Coarse-grained features,Fine-grained features

论文评审过程：Received 1 February 2020, Revised 4 April 2020, Accepted 17 April 2020, Available online 22 April 2020, Version of Record 6 May 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113465