Utilizing Large Language Models to Identify Evidence of Suicidality Risk through Analysis of Emotionally Charged Posts

Ahmet Yavuz Uluslu, Andrianos Michail, Simon Clematide


Abstract
This paper presents our contribution to the CLPsych 2024 shared task, focusing on the use of open-source large language models (LLMs) for suicide risk assessment through the analysis of social media posts. We achieved first place (out of 15 participating teams) in the task of providing summarized evidence of a user’s suicide risk. Our approach is based on Retrieval Augmented Generation (RAG), where we retrieve the top-k (k=5) posts with the highest emotional charge and provide the level of three different negative emotions (sadness, fear, anger) for each post during the generation phase.
Anthology ID:
2024.clpsych-1.26
Volume:
Proceedings of the 9th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2024)
Month:
March
Year:
2024
Address:
St. Julians, Malta
Editors:
Andrew Yates, Bart Desmet, Emily Prud’hommeaux, Ayah Zirikly, Steven Bedrick, Sean MacAvaney, Kfir Bar, Molly Ireland, Yaakov Ophir
Venues:
CLPsych | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
264–269
Language:
URL:
https://aclanthology.org/2024.clpsych-1.26
DOI:
Bibkey:
Cite (ACL):
Ahmet Yavuz Uluslu, Andrianos Michail, and Simon Clematide. 2024. Utilizing Large Language Models to Identify Evidence of Suicidality Risk through Analysis of Emotionally Charged Posts. In Proceedings of the 9th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2024), pages 264–269, St. Julians, Malta. Association for Computational Linguistics.
Cite (Informal):
Utilizing Large Language Models to Identify Evidence of Suicidality Risk through Analysis of Emotionally Charged Posts (Uluslu et al., CLPsych-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.clpsych-1.26.pdf
Video:
 https://aclanthology.org/2024.clpsych-1.26.mp4