Análisis de sentimiento de mensajes de correo electrónico bajo un enfoque de transfer learning

Abstract

Sentiment analysis by its acronym in Spanish (AS) also called opinion mining, is a field of study that analyzes people's opinions, feelings, evaluations, appreciations, attitudes and emotions about different entities (Liu, 2012). Using transfer learning techniques for sentiment analysis of emails, the quantity and quality of the data used is optimized, compared to traditional methods. The BERT-based model allowed reaching 79% completeness, reducing the effort in data pre-processing tasks. Click here to enter text.