SSN_Semeval10 at SemEval-2024 Task 10: Emotion Discovery and Reasoning its Flip in Conversations
A. V. P. Rajesh, Supriya Abirami, Aravindan Chandrabose, B. Senthil Kumar · 2024
This paper presents a transformer-based classifier for recognizing emotions in Hindi-English code-mixed conversations, adhering to the Se-mEval task constraints.Leveraging BERTbased transformers, we fine-tune pre-trained models (mBERT and indicBERT) on the dataset, incorporating tokenization and attention mechanisms.Our approach achieved competitive performance (weighted F1-score of 0.4), showcasing the effectiveness of BERT in nuanced emotion analysis tasks within codemixed conversational contexts.This F1-score was ranked 16 th among the 39 submissions.