Proceedings of the International Conference on Intelligent Data Analysis and Applications (IDAA 2025)

<Previous Article In Volume
Next Article In Volume>

CatForest: Deep Contextual Sentiment Modeling for Mental Health Detection from Social Media

Authors
Afsana Akter Tusa1, Md Jakaria Zobair1, *, Toufiq Mehraz1, Mahir Ashef2, Refat Tasfia Orpa3, Md Arifuzzaman4
1MARS Lab, Department of Computer Science and Engineering, Daffodil International University, Dhaka, 1216, Bangladesh
2Department of Computer Science and Engineering, Bangladesh University of Business and Technology, Dhaka, 1216, Bangladesh
3Department of Computer Science and Engineering, Hajee Mohammad Danesh Science and Technology University, Dinajpur, 5200, Bangladesh
4Department of Mathematics, East Texas A & M University, Commerce, Texas, USA
*Corresponding author. Email: jakariacse16@gmail.com
Corresponding Author
Md Jakaria Zobair
Available Online 8 June 2026.
DOI
10.2991/978-94-6239-664-7_26How to use a DOI?
Keywords
Mental Health Detection; Social Media; Machine Learning; Ensemble Models; Random Forest; SVM
Abstract

Mental health is one of the most important part of our overall well-being. Anxiety, depression, and emotional distress are becoming more common issues day-by-day for all age groups. People share their daily thoughts, emotions, and experiences on social media platforms such as Facebook, Twitter, and Instagram, which represent their mental states. In this study, we explored how machine learning can detect these signals by applying models like Logistic Regression (52.4% accuracy), Random Forest (97.08%), XGBoost (96.1%), and Support Vector Machines (79.6%). Among these, a newly developed hybrid model, CatForest, which combines the strengths of Random Forest with additional optimizations, performed the best, achieving 97.09% accuracy. CatForest shows strong potential for identifying emotional states through social media, which can be a promising tool for early and accessible mental health support. Dataset characteristics, ethical considerations, and evaluation processes are discussed to ensure reproducibility and reliability.

Copyright
© 2026 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the International Conference on Intelligent Data Analysis and Applications (IDAA 2025)
Series
Advances in Intelligent Systems Research
Publication Date
8 June 2026
ISBN
978-94-6239-664-7
ISSN
1951-6851
DOI
10.2991/978-94-6239-664-7_26How to use a DOI?
Copyright
© 2026 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Afsana Akter Tusa
AU  - Md Jakaria Zobair
AU  - Toufiq Mehraz
AU  - Mahir Ashef
AU  - Refat Tasfia Orpa
AU  - Md Arifuzzaman
PY  - 2026
DA  - 2026/06/08
TI  - CatForest: Deep Contextual Sentiment Modeling for Mental Health Detection from Social Media
BT  - Proceedings of the International Conference on Intelligent Data Analysis and Applications (IDAA 2025)
PB  - Atlantis Press
SP  - 371
EP  - 384
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-664-7_26
DO  - 10.2991/978-94-6239-664-7_26
ID  - Tusa2026
ER  -