A novel filter feature selection method using rough set for short text data

作者：

Highlights：

• A novel feature selection method is proposed for short text classification.

• The proposed method PRFS relies on rough set theory.

• PRFS makes a regional distinction as Positive, Negative, and Boundary for features.

• PRFS offers either better or competitive performance in terms of Macro-F1 scores.

• This study may be a pioneering study in this research field using rough set theory.

摘要

•A novel feature selection method is proposed for short text classification.•The proposed method PRFS relies on rough set theory.•PRFS makes a regional distinction as Positive, Negative, and Boundary for features.•PRFS offers either better or competitive performance in terms of Macro-F1 scores.•This study may be a pioneering study in this research field using rough set theory.

论文关键词：Short text classification,Rough set,Feature selection

论文评审过程：Received 4 February 2020, Revised 1 June 2020, Accepted 23 June 2020, Available online 6 July 2020, Version of Record 21 July 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113691