What does this research mean for the field?

Transformer-based models, specifically UrduBERT, can effectively classify anxiety and depression from Urdu social media text, achieving over 81% accuracy and outperforming traditional deep learning architectures. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

To develop a deep learning framework for classifying mental health conditions in Urdu through a large annotated dataset.

June 10, 2026Open Access

A large-scale annotated Urdu corpus and deep learning benchmark for mental health classification

Key Points

To develop a deep learning framework for classifying mental health conditions in Urdu through a large annotated dataset.
Created a publicly released dataset of 36,000 Urdu tweets classified into anxiety, depression, and neutral categories.
Evaluated three deep learning architectures: CNN+BiLSTM, CNN+BiGRU, and UrduBERT.
Validated dataset through systematic translation, manual annotation, and automated labeling.
UrduBERT achieved the highest accuracy of 81.71%, outperforming CNN+BiLSTM at 79.08% and CNN+BiGRU at 78.25%.
UrduBERT also displayed superior precision, recall, and F1-score across all categories.
Findings indicate the effectiveness of transformer-based models for mental health detection in low-resource languages.

Abstract

Abstract Millions of people worldwide are affected by mental health disorders, particularly anxiety and depression, which pose a growing health concern globally. Early detection and intervention are critical for improving treatment outcomes. Conventional clinical evaluation methods face significant barriers including limited accessibility, social stigma, and diagnostic delays. Recent advances in artificial intelligence and natural language processing have demonstrated promising capabilities for automated mental health detection through text analysis of social media. However, most existing research focuses exclusively on high-resource languages such as English, leaving a critical gap for low-resource languages. Our study addresses this limitation by developing a comprehensive deep learning framework for mental health classification in Urdu. More than 230 million people speak Urdu, but it is severely underrepresented in computational mental health research. This research provides the first large-scale, publicly released Urdu dataset specifically designed for multi-class anxiety, depression, and neutral classification, and establishes performance benchmarks for future work. We created and validated a novel annotated dataset of 36,000 Urdu tweets classified into anxiety, depression, and neutral categories through systematic translation, manual annotation, and automated labeling with rigorous quality validation. Three established deep learning architectures were adapted and systematically evaluated in this study. The CNN+BiLSTM model achieved an accuracy of 79.08%, while the CNN+BiGRU model attained 78.25%. Among all evaluated approaches, UrduBERT delivered the best performance with an accuracy of 81.71%, along with superior precision, recall, and F1-score values across all categories. These findings highlight the advantage of transformer-based contextual representations in modeling complex linguistic structures in morphologically rich languages. Overall, the proposed framework provides a strong basis for scalable and culturally sensitive mental health monitoring systems, with the potential to support early detection of at-risk individuals in linguistically underrepresented communities.

Ask AI

Helpful

Bookmark

View Full Paper