An Attention-based BERT–CNN–BiLSTM Model for Depression Detection From Emojis in Social Media Text
Loading...
Files
Size: 945.25 KB, File format: Adobe PDF
Date
Authors
Thekkekara, Joel Philip
Yongchareon, Sira
Supervisor
Item type
Degree name
Journal Title
Journal ISSN
Volume Title
Publisher
MDPI AG
Abstract
Depression represents a critical global mental health challenge, with social media offering unprecedented opportunities for early detection through computational analysis. We propose a novel BERT–CNN–BiLSTM architecture with attention mechanisms that systematically integrate emoji usage patterns—fundamental components of digital emotional expression overlooked by existing approaches. Evaluated on the SuicidEmoji dataset, our model achieves 97.12% accuracy, 94.56% precision, 93.44% F1-score, 85.67% MCC, and 91.23% AUC-ROC. Analysis reveals distinct emoji patterns: depressed users favour negative emojis (😔 13.9%, 😢 12.8%, 💔 6.7%) while controls prefer positive expressions (😂 16.5%, 😊 11.0%, 😎 10.2%). The attention mechanism identifies key linguistic markers, including emotional indicators, personal pronouns, and emoji features, providing interpretable insights into depression-related language. Our findings suggest that the integration of emojis substantially improves optimal social media-based mental health detection systems.
Description
Keywords
46 Information and Computing Sciences, 4608 Human-Centred Computing, Depression, Mental Illness, Mental Health, Brain Disorders, Behavioral and Social Science, 3 Good Health and Well Being, 46 Information and computing sciences, depression detection, natural language processing, deep learning, emoji analysis
Source
Big Data and Cognitive Computing, ISSN: 2504-2289 (Print); 2504-2289 (Online), MDPI AG, 9(12), 310-310. doi: 10.3390/bdcc9120310
Publisher's version
Rights statement
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.