A text classification approach to detect psychological stress combining a lexicon-based feature framework with distributional representations
作者：
Highlights：
• An approach for detecting stress from text is proposed.
• The approach combines lexicon-based features with distributional representations.
• Several kinds of feature sets are explored through a lexicon-based feature framework.
• Three word embedding techniques are studied to exploit distributional representations.
• The proposed approach is evaluated on three public English datasets.
摘要
•An approach for detecting stress from text is proposed.•The approach combines lexicon-based features with distributional representations.•Several kinds of feature sets are explored through a lexicon-based feature framework.•Three word embedding techniques are studied to exploit distributional representations.•The proposed approach is evaluated on three public English datasets.
论文关键词：Stress detection,Stress framework,Distributional representations,Text classification,Affective computing
论文评审过程：Received 29 March 2022, Revised 22 June 2022, Accepted 26 June 2022, Available online 1 July 2022, Version of Record 1 July 2022.
论文官网地址：https://doi.org/10.1016/j.ipm.2022.103011
