Comparación entre algoritmos de machine learning en la implementación del análisis de sentimientos para textos en español

Abstract

In this work, the sentiment analysis technique was used to process downloaded tweets in Spanish related to COVID-19. Using machine learning algorithms, neural networks, support vector machines and Bayesian classifiers. For this, the tweets were downloaded using a Twitter api, then a transformation was carried out on the texts and thus the training data for the different machine learning models was generated. Finally, different test scenarios were proposed, relating the results obtained at the end of the document.