Islam, ApuRafi, Ishraque ArefinMondal, SudiptaRahman, Somaya Al SadiaAlam, Golam Rabiul2026-08-152026-08-152025-01-01A. Islam, I. A. Rafi, S. Mondal, S. A. S. Rahman and G. R. Alam, "Which Matters More: Model or Language? An Empirical Study in English-Bangla Mental Health Classification," 2025 5th International Conference on Robotics, Automation, and Artificial Intelligence (RAAI), Singapore, Singapore, 2025, pp. 114-118, doi: 10.1109/RAAI67517.2025.11423350.97983315587342-s2.0-105035995762https://hdl.handle.net/10361/29091We present an empirical comparison of classical baselines and pretrained transformer encoders for mental health status classification across English and Bangla social media text. Using two public datasets-an English multi-class corpus and a Bangla binary corpus-we evaluate TF-IDF with Logistic Regression and Random Forest against BERT, RoBERTa, DeBERTa, and BanglaBERT under a matched setup with a stratified eighty twenty split and macro F1 for model selection. In English, RoBERTa achieves 81.6% accuracy with a macro F1 of 78.8, while TF-IDF with Logistic Regression reaches 77.3% accuracy. In Bangla, BanglaBERT attains 88.3% accuracy with a macro F 1 of 88.3, and classical baselines surpass several non-Bangla encoders. Findings highlight the value of language models and the importance of classical machine learning models in classifying mental status across different languages.114-118en-USfalseBanglaBanglaBERTBERTCrosslingual evaluationDeBERTa-v3Depression detectionEnglishLow-resource NLPMental health text classificationRoBERTaSocial mediaTransformer encodersBengali language.Mental health.Social media.Conference Proceeding10.1109/RAAI67517.2025.11423350