Automatic identification of emotions expressed in Twitter data has a wide range of applications. We create a well-balanced dataset by adding a neutral class to a benchmark dataset consisting of four emotions: fear, sadness, joy, and anger. On this extended dataset, we investigate the use of Support Vector Machine (SVM) and Bidirectional Encoder Representations from Transformers (BERT) for emotion recognition. We propose a novel ensemble model by combining the two BERT and SVM models. Experiments show that the proposed model achieves a state-of-the-art accuracy of 0.91 on emotion recognition in tweets.
@article{arxiv.2208.04547,
title = {Emotion Detection From Tweets Using a BERT and SVM Ensemble Model},
author = {Ionuţ-Alexandru Albu and Stelian Spînu},
journal= {arXiv preprint arXiv:2208.04547},
year = {2022}
}