Lannisters@DravidianLangTech 2026: A Comparative and Ablation Study of Multilingual Transformers for Gender-Targeted Abuse Detection in Tamil Social Media Platforms
Year: 2026
Type: conference-paper
Abstract: The prevalence of the use of the Tamil language on social media has heightened the need to address the issue of online harassment of women.As a result, there is a heightened need to develop a system to automatically identify abusive content in the Tamil language to promote a safe online communication platform.This paper presents a model to identify abusive content using a binary classification model to identify Abusive and Non-Abusive content.In this work, we experimented with several multilingual transformer models including DistilBERT, mBERT, and XLM-RoBERTa.From the experiments, it was observed that the XLM-RoBERTa model performed better than the others, achieving a validation accuracy of 91.17% and a validation macro F1 score of 0.8865.In this paper, ablation experiments are conducted to show that structured preprocessing, balancing the minority class, and tuning the hyperparameters contribute to the model's performance.
Authors: Kalaivani K S, Jaisanth K, Nandhini B
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Gender equality
Open Access status: hybrid
OpenAlex ID: W7166807299