Emotion-Infused Models for Explainable Psychological Stress Detection

Elsbeth Turcan, Smaranda Muresan, Kathleen McKeown


Abstract
The problem of detecting psychological stress in online posts, and more broadly, of detecting people in distress or in need of help, is a sensitive application for which the ability to interpret models is vital. Here, we present work exploring the use of a semantically related task, emotion detection, for equally competent but more explainable and human-like psychological stress detection as compared to a black-box model. In particular, we explore the use of multi-task learning as well as emotion-based language model fine-tuning. With our emotion-infused models, we see comparable results to state-of-the-art BERT. Our analysis of the words used for prediction show that our emotion-infused models mirror psychological components of stress.
Anthology ID:
2021.naacl-main.230
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2895–2909
Language:
URL:
https://aclanthology.org/2021.naacl-main.230
DOI:
10.18653/v1/2021.naacl-main.230
Bibkey:
Cite (ACL):
Elsbeth Turcan, Smaranda Muresan, and Kathleen McKeown. 2021. Emotion-Infused Models for Explainable Psychological Stress Detection. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2895–2909, Online. Association for Computational Linguistics.
Cite (Informal):
Emotion-Infused Models for Explainable Psychological Stress Detection (Turcan et al., NAACL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/nodalida-main-page/2021.naacl-main.230.pdf
Video:
 https://preview.aclanthology.org/nodalida-main-page/2021.naacl-main.230.mp4
Code
 eturcan/emotion-infused
Data
Dreaddit