UBIS: Unigram Bigram Importance Score for Feature Selection from Short Text

作者：

Highlights：

• Unigram Bigram Importance Score (UBIS) for feature selection.

• Graph-based method for short-text feature selection.

• Theoretical validation of UBIS for short-text classification.

• Comparative analysis with baselines for three publicly available datasets.

摘要

•Unigram Bigram Importance Score (UBIS) for feature selection.•Graph-based method for short-text feature selection.•Theoretical validation of UBIS for short-text classification.•Comparative analysis with baselines for three publicly available datasets.

论文关键词：Unigram importance score,Bigram importance score,Short text classification,Selective feature extraction

论文评审过程：Received 3 June 2021, Revised 28 December 2021, Accepted 17 January 2022, Available online 7 February 2022, Version of Record 16 February 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.116563