Monitoring Depression Severity and Symptoms in User-Generated Content: An Annotation Scheme and Guidelines

Falwah Alhamed, Rebecca Bendayan, Julia Ive, Lucia Specia


Abstract
Depression is a highly prevalent condition recognized by the World Health Organization as a leading contributor to global disability. Many people suffering from depression express their thoughts and feelings using social media, which thus becomes a source of data for research in this domain. However, existing annotation schemes tailored to studying depression symptoms in social media data remain limited. Reliable and valid annotation guidelines are crucial for accurately measuring mental health conditions for those studies. This paper addresses this gap by presenting a novel depression annotation scheme and guidelines for detecting depression symptoms and their severity in social media text. Our approach leverages validated depression questionnaires and incorporates the expertise of psychologists and psychiatrists during scheme refinement. The resulting annotation scheme achieves high inter-rater agreement, demonstrating its potential for suitable depression assessment in social media contexts.
Anthology ID:
2024.wassa-1.18
Volume:
Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Orphée De Clercq, Valentin Barriere, Jeremy Barnes, Roman Klinger, João Sedoc, Shabnam Tafreshi
Venues:
WASSA | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
227–233
Language:
URL:
https://aclanthology.org/2024.wassa-1.18
DOI:
10.18653/v1/2024.wassa-1.18
Bibkey:
Cite (ACL):
Falwah Alhamed, Rebecca Bendayan, Julia Ive, and Lucia Specia. 2024. Monitoring Depression Severity and Symptoms in User-Generated Content: An Annotation Scheme and Guidelines. In Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis, pages 227–233, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Monitoring Depression Severity and Symptoms in User-Generated Content: An Annotation Scheme and Guidelines (Alhamed et al., WASSA-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.wassa-1.18.pdf