Back

Detecting Mental Disorders in Social Media Using a Transformer-Based Ensemble of Binary Classifiers

2025-12-18 health informatics Title + abstract only
View on medRxiv
Show abstract

This study introduces a novel transformer-based ensemble framework for the multi-label detection of mental health disorders from social media posts. Unlike traditional multi-class approaches that often struggle with comorbidity, the proposed method employs a binary relevance strategy using fine-tuned DistilBERT models to identify co-occurring conditions, including depression, anxiety, and narcissistic personality disorder. To address class imbalance and optimize decision boundaries, the framewor...

Predicted journal destinations

1
Journal of Medical Internet Research
81 training papers
Top 0.3% 13.9%
2
Scientific Reports
701 training papers
Top 15% 11.3%
3
PLOS ONE
1737 training papers
Top 68% 7.4%
4
PLOS Digital Health
88 training papers
Top 2% 7.4%
5
JAMIA Open
35 training papers
Top 2% 6.1%
6
Journal of Biomedical Informatics
37 training papers
Top 2% 6.1%
7
Journal of the American Medical Informatics Association
53 training papers
Top 3% 6.1%
8
BMC Medical Informatics and Decision Making
36 training papers
Top 3% 5.7%
9
npj Digital Medicine
85 training papers
Top 4% 5.7%
10
Frontiers in Psychiatry
56 training papers
Top 4% 4.0%
11
International Journal of Medical Informatics
25 training papers
Top 1% 3.7%
12
JMIR Medical Informatics
16 training papers
Top 3% 1.8%
13
Computers in Biology and Medicine
39 training papers
Top 4% 1.8%
14
JMIR Formative Research
31 training papers
Top 1% 1.8%
15
Translational Psychiatry
94 training papers
Top 8% 1.3%
16
Frontiers in Digital Health
18 training papers
Top 1% 1.3%
17
Patterns
15 training papers
Top 0.7% 1.3%
18
Frontiers in Public Health
135 training papers
Top 24% 1.3%
19
PLOS Computational Biology
141 training papers
Top 12% 1.0%
20
International Journal of Environmental Research and Public Health
116 training papers
Top 28% 0.9%
21
BMC Medical Research Methodology
41 training papers
Top 7% 0.9%
22
JMIR Public Health and Surveillance
45 training papers
Top 6% 0.9%
23
Psychological Medicine
52 training papers
Top 7% 0.7%