Symptom Identification for Interpretable Detection of Multiple Mental Disorders on Social Media

Zhiling Zhang, Siyuan Chen, Mengyue Wu, Kenny Zhu


Abstract
Mental disease detection (MDD) from social media has suffered from poor generalizability and interpretability, due to lack of symptom modeling. This paper introduces PsySym, the first annotated symptom identification corpus of multiple psychiatric disorders, to facilitate further research progress. PsySym is annotated according to a knowledge graph of the 38 symptom classes related to 7 mental diseases complied from established clinical manuals and scales, and a novel annotation framework for diversity and quality. Experiments show that symptom-assisted MDD enabled by PsySym can outperform strong pure-text baselines. We also exhibit the convincing MDD explanations provided by symptom predictions with case studies, and point to their further potential applications.
Anthology ID:
2022.emnlp-main.677
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9970–9985
Language:
URL:
https://aclanthology.org/2022.emnlp-main.677
DOI:
10.18653/v1/2022.emnlp-main.677
Bibkey:
Cite (ACL):
Zhiling Zhang, Siyuan Chen, Mengyue Wu, and Kenny Zhu. 2022. Symptom Identification for Interpretable Detection of Multiple Mental Disorders on Social Media. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 9970–9985, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Symptom Identification for Interpretable Detection of Multiple Mental Disorders on Social Media (Zhang et al., EMNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/2022.emnlp-main.677.pdf