Helpfulness of online consumer reviews: A multi-perspective approach

作者：

Highlights：

• Helpfulness of online review represented with three qualitative perspectives.

• N-gram, sequential semantics and structural statistics are implemented.

• Deep learning modules like LSTM, and d-CNN are used for semantic perspectives.

• Human scoring is used to address the problem related to helpfulness voting.

• Weights of each of the perspectives on helpfulness of a review is estimated.

摘要

•Helpfulness of online review represented with three qualitative perspectives.•N-gram, sequential semantics and structural statistics are implemented.•Deep learning modules like LSTM, and d-CNN are used for semantic perspectives.•Human scoring is used to address the problem related to helpfulness voting.•Weights of each of the perspectives on helpfulness of a review is estimated.

论文关键词：Helpfulness of review,Perspectives of helpfulness, Convolutional neural network,LSTM,Regression analysis,Deep learning

论文评审过程：Received 16 October 2020, Revised 7 January 2021, Accepted 31 January 2021, Available online 8 February 2021, Version of Record 8 February 2021.

论文官网地址：https://doi.org/10.1016/j.ipm.2021.102538