False narratives that manipulate racial tensions are increasingly prevalent on social media, often blending languages and cultural references to enhance reach and believability. Among them, racial hoaxes produce unique harm by fabricating events targeting specific communities, social division and fueling misinformation. This paper presents a novel approach to detecting racial hoaxes in code-mixed Hindi-English social media data. Using a carefully constructed training pipeline, we have fine-tuned the XLM-RoBERTa-base multilingual transformer for training the shared task data. Our approach has incorporated task-specific preprocessing, clear methodology, and extensive hyperparameter tuning. After developing our model, we tested and evaluated it on the LT-EDI@LDK 2025 shared task dataset. Our system achieved the highest performance among all the international participants with an F1-score of 0.75, ranking 1st on the official leaderboard.

Hate speech on social media is an evolving problem, particularly in low-resource languages like Tamil, where traditional hate speech detection approaches remain under developed. In this work, we provide a focused solution for cast and migration-based hate speech detection using Tamil-BERT, a Tamil-specialized pre-trained transformer model. One of the key challenges in hate speech detection is the severe class imbalance in the dataset, with hate speech being the minority class. We solve this using focal loss, a loss function that gives more importance to harder-to-classify examples, improving the performance of the model in detecting minority classes. We train our model on a publicly available labeled dataset of Tamil text as hate and non-hate speech. Under strict evaluation, our approach achieves impressive results, outperforming baseline models by a considerable margin. The model achieves an F1 score of 0.8634 and good precision, recall, and accuracy, making it a robust solution for hate speech detection in Tamil. The results show that fine-tuning transformer-based models like Tamil-BERT, coupled with techniques like focal loss, can substantially improve performance in hate speech detection for low-resource languages. This work is a contribution to this growing amount of research and provides insights on how to tackle class imbalance for NLP tasks.

Due to technological advancements, various methods have emerged for disseminating news to the masses. The pervasive reach of news, however, has given rise to a significant concern: the proliferation of fake news. In response to this challenge, a shared task in Dravidian- LangTech EACL2024 was initiated to detect fake news and classify its types in the Malayalam language. The shared task consisted of two sub-tasks. Task 1 focused on a binary classification problem, determining whether a piece of news is fake or not. Whereas task 2 delved into a multi-class classification problem, categorizing news into five distinct levels. Our approach involved the exploration of various machine learning (RF, SVM, XGBoost, Ensemble), deep learning (BiLSTM, CNN), and transformer-based models (MuRIL, Indic- SBERT, m-BERT, XLM-R, Distil-BERT) by emphasizing parameter tuning to enhance overall model performance. As a result, we introduce a fine-tuned MuRIL model that leverages parameter tuning, achieving notable success with an F1-score of 0.86 in task 1 and 0.5191 in task 2. This successful implementation led to our system securing the 3rd position in task 1 and the 1st position in task 2. The source code will be found in the GitHub repository at this link: https://github.com/Salman1804102/ DravidianLangTech-EACL-2024-FakeNews.

Textual Sentiment Analysis (TSA) delves into people’s opinions, intuitions, and emotions regarding any entity. Natural Language Processing (NLP) serves as a technique to extract subjective knowledge, determining whether an idea or comment leans positive, negative, neutral, or a mix thereof toward an entity. In recent years, it has garnered substantial attention from NLP researchers due to the vast availability of online comments and opinions. Despite extensive studies in this domain, sentiment analysis in low-resourced languages such as Tamil and Tulu needs help handling code-mixed and transliterated content. To address these challenges, this work focuses on sentiment analysis of code-mixed and transliterated Tamil and Tulu social media comments. It explored four machine learning (ML) approaches (LR, SVM, XGBoost, Ensemble), four deep learning (DL) methods (BiLSTM and CNN with FastText and Word2Vec), and four transformer-based models (m-BERT, MuRIL, L3Cube-IndicSBERT, and Distilm-BERT) for both languages. For Tamil, L3Cube-IndicSBERT and ensemble approaches outperformed others, while m-BERT demonstrated superior performance among the models for Tulu. The presented models achieved the 3^rd and 1^st ranks by attaining macro F1-scores of 0.227 and 0.584 in Tamil and Tulu, respectively.