Emotions classification on social media comments using machine learning and deep learning models

Abstract

This research addresses emotion recognition in Vietnamese text using traditional machine learning (SVM, Logistic Regression) and deep learning (MLP, BiLSTM) models. Key contributions include a comprehensive emotion recognition pipeline with preprocessing techniques like stopword removal, teencode normalization, and emoji handling. The study demonstrates that TF-IDF embeddings yield high performance in traditional models, while BiLSTM with Word2Vec excels in capturing sequential relationships. The models were deployed on Streamlit Cloud for real-time emotion prediction. This work highlights the potential applications of this research in Vietnamese emotion analysis on social, supporting businesses and researchers in understanding user opinions effectively