Oslcfit (organic simultaneous LSTM and CNN Fit): A novel deep learning based solution for sentiment polarity classification of reviews

作者：

Highlights：

• Novel deep learning framework OSLCFit for review sentiment polarity classification.

• Single architecture combining CNN and LSTM features trained with single optimizer.

• Variable region & temporal dependency from LSTM; Fixed length features from CNN.

• Comparative analysis with state-of-the-art measures on 6 benchmark review datasets.

• OSLCFit out-performs existing methods and scales well to large datasets.

摘要

•Novel deep learning framework OSLCFit for review sentiment polarity classification.•Single architecture combining CNN and LSTM features trained with single optimizer.•Variable region & temporal dependency from LSTM; Fixed length features from CNN.•Comparative analysis with state-of-the-art measures on 6 benchmark review datasets.•OSLCFit out-performs existing methods and scales well to large datasets.

论文关键词：Bi-directional LSTM,CNN,Sentiment Classification,Organic Simultaneous LSTM and CNN Fit,Review Polarity,NLP

论文评审过程：Received 20 July 2019, Revised 26 April 2020, Accepted 26 April 2020, Available online 1 May 2020, Version of Record 11 May 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113488