RT Journal Article
T1 Adapting language models for mental health analysis on social media
A1 Aragón Saenzpardo, Mario Ezra
A1 López Monroy, Adrián Pastor
A1 Montes y Gómez, Manuel
A1 Losada Carril, David Enrique
K1 Social media
K1 Mental health
K1 Anorexia
K1 Depression
K1 Gambling
K1 Self-harm
K1 Language models
K1 Adapters
AB In recent years, there has been a growing research interest focused on identifying traces of mental disorders through social media analysis. These disorders significantly impair millions of individuals’ cognitive and behavioral functions worldwide. Our study aims to advance the understanding of four prevalent mental disorders: Anorexia, Depression, Gambling, and Self-harm. We present a comprehensive framework designed for the domain adaptation of models to analyze and identify signs of these conditions on social media posts. The language models’ adapting strategy consisted of three key stages. First, we gathered and enriched substantial data on the four psychological disorders. Second, we adapted the different models to the language used to discuss mental health concerns on social media. Finally, we employed an adapter to fine-tune the models for multiple classification tasks (specific to each mental health condition). The intuitive idea is to adapt a language model smoothly to each domain. Our work includes a comparative study of different language models under in- and cross-domain conditions. This allows us to, for example, assess the ability of a depression-based language model to detect signs of disorders such as anorexia or self-harm. We show that the resulting mental health models perform well in early risk detection tasks. Additionally, we thoroughly analyze the linguistic qualities of these models by testing their predictive abilities using conventional clinical tools, such as specialized questionnaires. We rigorously examine the models across multiple predictive tasks to provide evidence of the adaptation approach’s robustness and effectiveness. Our evaluation results are promising. They demonstrate that our framework enhances classification performance and competes favorably with state-of-the-art models.
PB Elsevier
SN 0933-3657
YR 2025
FD 2025-07-16
LK https://hdl.handle.net/10347/43901
UL https://hdl.handle.net/10347/43901
LA eng
NO Aragón, M. E., López-Monroy, A. P., Montes-y-Gómez, M., & Losada, D. E. (2025). Adapting language models for mental health analysis on social media. Artificial Intelligence in Medicine, 168, 103217. 10.1016/j.artmed.2025.103217
NO Mario Ezra Aragón and David E. Losada, thank the support obtained from MICIU/AEI/10.13039/501100011033 (PID2022-137061OB-C22, supported by ERDF) and Xunta de Galicia-Consellería de Cultura, Educación, Formación Profesional e Universidades (ED431G 2023/04, ED431C 2022/19, supported by ERDF).
DS Minerva
RD 28 abr 2026