Ordinal-based and frequency-based integration of feature selection methods for sentiment analysis

作者：

Highlights：

• We propose two methods for integrating feature selection in sentiment analysis.

• Based on these methods a new ranking feature vector is created.

• Results show important potential in facilitating the sentiment classification.

摘要

•We propose two methods for integrating feature selection in sentiment analysis.•Based on these methods a new ranking feature vector is created.•Results show important potential in facilitating the sentiment classification.

论文关键词：Feature selection,Ordinal-based integration,Frequency-based integration,Feature vectors integration,Feature subsets integration,Sentiment analysis

论文评审过程：Received 9 July 2015, Revised 4 January 2017, Accepted 9 January 2017, Available online 17 January 2017, Version of Record 31 January 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.01.009