Affective Computing is the study of how computers can recognize, interpret and simulate human affects. Sentiment Analysis is a common task inNLP related to this topic, but it focuses only on emotion valence (positive, negative, neutral). An emerging approach in NLP is Emotion Recognition, which relies on fined-grained classification. This research describes an approach to create a lexical-based weakly supervised corpus for fine-grained emotion in Portuguese. We evaluated our dataset by fine-tuning a transformer-based language model (BERT) and validating it on a Gold Standard annotated validation set. Our results (F1-score=.64) suggest lexical-based weak supervision as an appropriate strategy for initial work in low resourced environment.
@article{arxiv.2108.07638,
title = {A Weakly Supervised Dataset of Fine-Grained Emotions in Portuguese},
author = {Diogo Cortiz and Jefferson O. Silva and Newton Calegari and Ana Luísa Freitas and Ana Angélica Soares and Carolina Botelho and Gabriel Gaudencio Rêgo and Waldir Sampaio and Paulo Sergio Boggio},
journal= {arXiv preprint arXiv:2108.07638},
year = {2021}
}
Comments
Paper published at Symposium in Information and Human Language Technology (STIL 2021)