A novel framework for seasonal affective disorder detection
Comprehensive machine learning analysis using multimodal social media data and SMOTE
Bibliographic Data
| ID | 9406501 |
|---|---|
| Authors | Md Shamshuzzoha (0009-0003-1052-1424, United International University), Tazkia Tasnim Bahar Audry (United International University), Md Jahangir Alam (0000-0002-1025-7067, Morgan State University), Zaheed Ahmed Bhuiyan (0009-0008-6937-0559, United International University), Md Motaharul Islam (0000-0002-8030-3225, United International University, corresponding author), Mohammad Mehedi Hassan (0000-0002-3479-3606, King Saud University) |
| Year | 2025 |
| Volume | 256 |
| Pages | 105005-105005 |
| Publication date | 2025-05-05 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Acta Psychologica (JOURNAL) |
| Journal identifiers | ISSN: 0001-6918 • E-ISSN: 1873-6297 |
| Publisher | Elsevier BV (PUBLISHER) |
| DOI | 10.1016/j.actpsy.2025.105005 |
| PMID | 40328104 |
| OpenAlex | W4410084012 |
| Language | EN |
| Citations received | 1 |
| References cited | 35 |
Seasonal Affective Disorder (SAD) is a mood disorder characterized by recurring depressive episodes during specific seasons, particularly in Fall and Winter. With the rise of social media as a platform for self-expression, user-generated content offers valuable insights into mental health trends, presenting an opportunity for data-driven SAD detection. However, existing research faces challenges such as limited multimodal datasets, class imbalance, and the need for real-time predictive models. This study addresses these gaps by curating a unique social media dataset that captures seasonal patterns and employing advanced machine learning techniques for accurate SAD detection. We apply the Synthetic Minority Over-sampling Technique (SMOTE) in two distinct ways-on the training dataset post-splitting and the entire dataset-to assess its impact on model generalization. Our findings highlight Random Forest, LGBM, and XGBoost as the top-performing models, with K-Nearest Neighbors (KNN) achieving the highest accuracy of 97.87 % in the training dataset. Additionally, we optimize computational efficiency to ensure real-time scalability for large-scale social media data processing. This research advances SAD detection by integrating robust dataset curation, class imbalance mitigation, and machine learning optimization, paving the way for more effective mental health monitoring through social media analytics
Emotion detection · Emotion recognition · Machine learning · Pattern recognition (psychology · Social media · World Wide Web · Artificial Intelligence · Computer Science · Digital Mental Health Interventions · Mental Health via Writing · Psychology · Sentiment Analysis and Opinion Mining
| Citations per year | 1 |
|---|---|
| Citation span | 2026 - 2026 (1) |
| Highly cited | No |