A novel framework for seasonal affective disorder detection: Comprehensive machine learning analysis using multimodal social media data and SMOTE

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, pr...

Full description

Saved in:
Bibliographic Details
Main Authors: Md. Shamshuzzoha, Tazkia Tasnim Bahar Audry, Md. Jahangir Alam, Zaheed Ahmed Bhuiyan, Md Motaharul Islam, Mohammad Mehedi Hassan
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Acta Psychologica
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S000169182500318X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849727855780429824
author Md. Shamshuzzoha
Tazkia Tasnim Bahar Audry
Md. Jahangir Alam
Zaheed Ahmed Bhuiyan
Md Motaharul Islam
Mohammad Mehedi Hassan
author_facet Md. Shamshuzzoha
Tazkia Tasnim Bahar Audry
Md. Jahangir Alam
Zaheed Ahmed Bhuiyan
Md Motaharul Islam
Mohammad Mehedi Hassan
author_sort Md. Shamshuzzoha
collection DOAJ
description 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.
format Article
id doaj-art-d080fea6ee4e4744b2030f0c8df3ef7d
institution DOAJ
issn 0001-6918
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series Acta Psychologica
spelling doaj-art-d080fea6ee4e4744b2030f0c8df3ef7d2025-08-20T03:09:44ZengElsevierActa Psychologica0001-69182025-06-0125610500510.1016/j.actpsy.2025.105005A novel framework for seasonal affective disorder detection: Comprehensive machine learning analysis using multimodal social media data and SMOTEMd. Shamshuzzoha0Tazkia Tasnim Bahar Audry1Md. Jahangir Alam2Zaheed Ahmed Bhuiyan3Md Motaharul Islam4Mohammad Mehedi Hassan5Department of Computer Science and Engineering, United International University, United City, Madani Avenue, Badda, Dhaka 1212, BangladeshDepartment of Computer Science and Engineering, United International University, United City, Madani Avenue, Badda, Dhaka 1212, BangladeshDepartment of Electrical and Computer Engineering, Morgan State University, 1700, E Cold Spring Ln, Baltimore, MD 21251, United StatesDepartment of Computer Science and Engineering, United International University, United City, Madani Avenue, Badda, Dhaka 1212, BangladeshDepartment of Computer Science and Engineering, United International University, United City, Madani Avenue, Badda, Dhaka 1212, Bangladesh; Corresponding author.Department of Information Systems, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi ArabiaSeasonal 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.http://www.sciencedirect.com/science/article/pii/S000169182500318XSADSocial media analyticsSentiment analysisSAD detectionMLSMOTE
spellingShingle Md. Shamshuzzoha
Tazkia Tasnim Bahar Audry
Md. Jahangir Alam
Zaheed Ahmed Bhuiyan
Md Motaharul Islam
Mohammad Mehedi Hassan
A novel framework for seasonal affective disorder detection: Comprehensive machine learning analysis using multimodal social media data and SMOTE
Acta Psychologica
SAD
Social media analytics
Sentiment analysis
SAD detection
ML
SMOTE
title A novel framework for seasonal affective disorder detection: Comprehensive machine learning analysis using multimodal social media data and SMOTE
title_full A novel framework for seasonal affective disorder detection: Comprehensive machine learning analysis using multimodal social media data and SMOTE
title_fullStr A novel framework for seasonal affective disorder detection: Comprehensive machine learning analysis using multimodal social media data and SMOTE
title_full_unstemmed A novel framework for seasonal affective disorder detection: Comprehensive machine learning analysis using multimodal social media data and SMOTE
title_short A novel framework for seasonal affective disorder detection: Comprehensive machine learning analysis using multimodal social media data and SMOTE
title_sort novel framework for seasonal affective disorder detection comprehensive machine learning analysis using multimodal social media data and smote
topic SAD
Social media analytics
Sentiment analysis
SAD detection
ML
SMOTE
url http://www.sciencedirect.com/science/article/pii/S000169182500318X
work_keys_str_mv AT mdshamshuzzoha anovelframeworkforseasonalaffectivedisorderdetectioncomprehensivemachinelearninganalysisusingmultimodalsocialmediadataandsmote
AT tazkiatasnimbaharaudry anovelframeworkforseasonalaffectivedisorderdetectioncomprehensivemachinelearninganalysisusingmultimodalsocialmediadataandsmote
AT mdjahangiralam anovelframeworkforseasonalaffectivedisorderdetectioncomprehensivemachinelearninganalysisusingmultimodalsocialmediadataandsmote
AT zaheedahmedbhuiyan anovelframeworkforseasonalaffectivedisorderdetectioncomprehensivemachinelearninganalysisusingmultimodalsocialmediadataandsmote
AT mdmotaharulislam anovelframeworkforseasonalaffectivedisorderdetectioncomprehensivemachinelearninganalysisusingmultimodalsocialmediadataandsmote
AT mohammadmehedihassan anovelframeworkforseasonalaffectivedisorderdetectioncomprehensivemachinelearninganalysisusingmultimodalsocialmediadataandsmote
AT mdshamshuzzoha novelframeworkforseasonalaffectivedisorderdetectioncomprehensivemachinelearninganalysisusingmultimodalsocialmediadataandsmote
AT tazkiatasnimbaharaudry novelframeworkforseasonalaffectivedisorderdetectioncomprehensivemachinelearninganalysisusingmultimodalsocialmediadataandsmote
AT mdjahangiralam novelframeworkforseasonalaffectivedisorderdetectioncomprehensivemachinelearninganalysisusingmultimodalsocialmediadataandsmote
AT zaheedahmedbhuiyan novelframeworkforseasonalaffectivedisorderdetectioncomprehensivemachinelearninganalysisusingmultimodalsocialmediadataandsmote
AT mdmotaharulislam novelframeworkforseasonalaffectivedisorderdetectioncomprehensivemachinelearninganalysisusingmultimodalsocialmediadataandsmote
AT mohammadmehedihassan novelframeworkforseasonalaffectivedisorderdetectioncomprehensivemachinelearninganalysisusingmultimodalsocialmediadataandsmote