Minería de texto para el análisis de sentimientos, en procesos de enseñanza aprendizaje al utilizar la red social Facebook

Abstract

Abstract:Machine learning algorithms are widely used in text mining problems, in this specific work they were used to perform sentiment analysis. The textual corpus in which the algorithms were tested was generated from interactions that students and teachers had in study groups created on the social network Facebook. Two algorithms were tested: Support Vector Machine and Complement Naïve Bayes. The results obtained showed that, based on metrics such as Recall, precision and the F1 score, the algorithm with the best performance is the Complement Naïve Bayes.