CUET_Novice@DravidianLangTech 2025: A Bi-GRU Approach for Multiclass Political Sentiment Analysis of Tamil Twitter (X) Comments
Arupa Barua, Md Osama, Ashim Dey · 2025
Multilingual political sentiment analysis faces challenges in capturing subtle variations, especially in complex and low-resourced languages.Identifying sentiments correctly is crucial to understanding public discourse.A shared task on Political Multiclass Sentiment Analysis of Tamil X (Twitter) Comments, organized by Dra-vidianLangTech@NAACL 2025, provided an opportunity to tackle these challenges.For this task, we implemented two data augmentation techniques, which are synonym replacement and back translation, and then explored various machine learning (ML) algorithms.We experimented with deep learning (DL) models including GRU, BiLSTM, BiGRU, hybrid CNN-GRU and CNN-BiLSTM to capture the semantic meanings more efficiently using Fast-Text and CBOW embedding.The Bidirectional Gated Recurrent Unit (BiGRU) achieved the best macro-F1 (MF1) score of 0.33, securing the 17th position in the shared task.These findings underscore the challenges of political sentiment analysis in low-resource languages and the need for advanced language-specific models for improved classification.