CUET_HateShield@NLU of Devanagari Script Languages 2025: Transformer-Based Hate Speech Detection in Devanagari Script Languages

Sumaiya Rahman Aodhora, Shawly Ahsan, Mohammed Moshiul Hoque


Abstract
Social media has become a vital platform for information exchange and free expression, yet its open nature also contributes to the spread of harmful content, including hate speech, cyberbullying, and offensive language, posing serious risks to societal well-being. Such content is linked to adverse impacts, including mental health issues. This study aims to develop an automated system for detecting hate speech in Devanagari script languages, enabling efficient moderation and prompt intervention. Our approach utilizes a fine-tuned transformer model to classify offensive content. We experimented with various machine learning (Logistic Regression, SVM, Ensemble methods) and deep learning architectures (CNN, BiLSTM, CNN-BiLSTM) alongside transformer-based models (Indic-SBERT, m-BERT, MuRIL, Indic-SBERT, XLM-R). Notably, the fine-tuned XLM-Roberta model achieved the highest performance, reaching a macro-average F1-score of 0.74, demonstrating its efficacy in detecting hate speech in Devanagari script languages. However, the model we submitted achieved a macro-average F1-score of 0.73, securing 13th place in the subtask.
Anthology ID:
2025.chipsal-1.28
Volume:
Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025)
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Kengatharaiyer Sarveswaran, Ashwini Vaidya, Bal Krishna Bal, Sana Shams, Surendrabikram Thapa
Venues:
CHiPSAL | WS
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
260–266
Language:
URL:
https://aclanthology.org/2025.chipsal-1.28/
DOI:
Bibkey:
Cite (ACL):
Sumaiya Rahman Aodhora, Shawly Ahsan, and Mohammed Moshiul Hoque. 2025. CUET_HateShield@NLU of Devanagari Script Languages 2025: Transformer-Based Hate Speech Detection in Devanagari Script Languages. In Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025), pages 260–266, Abu Dhabi, UAE. International Committee on Computational Linguistics.
Cite (Informal):
CUET_HateShield@NLU of Devanagari Script Languages 2025: Transformer-Based Hate Speech Detection in Devanagari Script Languages (Aodhora et al., CHiPSAL 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.chipsal-1.28.pdf