Modified DFS-based term weighting scheme for text classification

作者：

Highlights：

• For text classification, different terms have different levels of importance.

• Designing an appropriate term weighting scheme is crucial.

• Distinguishing feature selector (DFS) is a well-known term selection scheme.

• We propose a modified DFS-based term weighting scheme.

• The experimental results validate the effectiveness of the proposed scheme.

摘要

•For text classification, different terms have different levels of importance.•Designing an appropriate term weighting scheme is crucial.•Distinguishing feature selector (DFS) is a well-known term selection scheme.•We propose a modified DFS-based term weighting scheme.•The experimental results validate the effectiveness of the proposed scheme.

论文关键词：Text classification,Term weighting,Term frequency,Distinguishing feature selector

论文评审过程：Received 3 April 2020, Revised 17 August 2020, Accepted 2 December 2020, Available online 7 December 2020, Version of Record 9 December 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.114438