Combining Psychological Theory with Language Models for Suicide Risk Detection

Daniel Izmaylov, Avi Segal, Kobi Gal, Meytal Grimland, Yossi Levi-Belz


Abstract
With the increased awareness of situations of mental crisis and their societal impact, online services providing emergency support are becoming commonplace in many countries. Computational models, trained on discussions between help-seekers and providers, can support suicide prevention by identifying at-risk individuals. However, the lack of domain-specific models, especially in low-resource languages, poses a significant challenge for the automatic detection of suicide risk. We propose a model that combines pre-trained language models (PLM) with a fixed set of manually crafted (and clinically approved) set of suicidal cues, followed by a two-stage fine-tuning process. Our model achieves 0.91 ROC-AUC and an F2-score of 0.55, significantly outperforming an array of strong baselines even early on in the conversation, which is critical for real-time detection in the field. Moreover, the model performs well across genders and age groups.
Anthology ID:
2023.findings-eacl.184
Volume:
Findings of the Association for Computational Linguistics: EACL 2023
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2430–2438
Language:
URL:
https://aclanthology.org/2023.findings-eacl.184
DOI:
10.18653/v1/2023.findings-eacl.184
Bibkey:
Cite (ACL):
Daniel Izmaylov, Avi Segal, Kobi Gal, Meytal Grimland, and Yossi Levi-Belz. 2023. Combining Psychological Theory with Language Models for Suicide Risk Detection. In Findings of the Association for Computational Linguistics: EACL 2023, pages 2430–2438, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Combining Psychological Theory with Language Models for Suicide Risk Detection (Izmaylov et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-eacl.184.pdf
Video:
 https://aclanthology.org/2023.findings-eacl.184.mp4