Improved inverse gravity moment term weighting for text classification

作者：

Highlights：

• Two novel term weighting schemes are proposed for text classification.

• The proposed schemes are named as SQRT_TF-IGMimp and TF-IGMimp.

• These schemes are derived from standard inverse gravity moment formula.

• SQRT_TF-IGMimp method generally outperformed all other schemes.

• The performance gains of the SQRT_TF-IGMimp scheme are statistically significant.

摘要

•Two novel term weighting schemes are proposed for text classification.•The proposed schemes are named as SQRT_TF-IGMimp and TF-IGMimp.•These schemes are derived from standard inverse gravity moment formula.•SQRT_TF-IGMimp method generally outperformed all other schemes.•The performance gains of the SQRT_TF-IGMimp scheme are statistically significant.

论文关键词：Text classification,Term weighting,Inverse gravity moment (IGM)

论文评审过程：Received 21 December 2018, Revised 2 April 2019, Accepted 6 April 2019, Available online 9 April 2019, Version of Record 15 April 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.04.015