Suicide Risk Assessment with Multi-level Dual-Context Language and BERT

Matthew Matero, Akash Idnani, Youngseo Son, Salvatore Giorgi, Huy Vu, Mohammad Zamani, Parth Limbachiya, Sharath Chandra Guntuku, H. Andrew Schwartz


Abstract
Mental health predictive systems typically model language as if from a single context (e.g. Twitter posts, status updates, or forum posts) and often limited to a single level of analysis (e.g. either the message-level or user-level). Here, we bring these pieces together to explore the use of open-vocabulary (BERT embeddings, topics) and theoretical features (emotional expression lexica, personality) for the task of suicide risk assessment on support forums (the CLPsych-2019 Shared Task). We used dual context based approaches (modeling content from suicide forums separate from other content), built over both traditional ML models as well as a novel dual RNN architecture with user-factor adaptation. We find that while affect from the suicide context distinguishes with no-risk from those with “any-risk”, personality factors from the non-suicide contexts provide distinction of the levels of risk: low, medium, and high risk. Within the shared task, our dual-context approach (listed as SBU-HLAB in the official results) achieved state-of-the-art performance predicting suicide risk using a combination of suicide-context and non-suicide posts (Task B), achieving an F1 score of 0.50 over hidden test set labels.
Anthology ID:
W19-3005
Volume:
Proceedings of the Sixth Workshop on Computational Linguistics and Clinical Psychology
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Venue:
CLPsych
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
39–44
Language:
URL:
https://aclanthology.org/W19-3005
DOI:
10.18653/v1/W19-3005
Bibkey:
Cite (ACL):
Matthew Matero, Akash Idnani, Youngseo Son, Salvatore Giorgi, Huy Vu, Mohammad Zamani, Parth Limbachiya, Sharath Chandra Guntuku, and H. Andrew Schwartz. 2019. Suicide Risk Assessment with Multi-level Dual-Context Language and BERT. In Proceedings of the Sixth Workshop on Computational Linguistics and Clinical Psychology, pages 39–44, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Suicide Risk Assessment with Multi-level Dual-Context Language and BERT (Matero et al., CLPsych 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-3005.pdf