Regresar

Analysis of feelings in messages received in the virtual learning environment of the open and distance modality of the utpl

Abstract:

This project pretends to analyze and classify the messages sent through the Virtual Learning Environment (EVA) of the Technical University of Loja. The aim of it is to know the level of positivism or negativism on students through automatic learning techniques. Different text mining methods are identified and applied to calculate the polarity of messages. The process has several phases. First, it starts by obtaining information from EVA. Then, the messages are stored and analysed in a repository, the data which does not contribute is eliminated and left in an established format. The “Sentiment Analysis” is executed for this; it uses different classification methods: R using Tidy, in java the stanford.nlp framework, with Python the methods were executed: Naive Bayes, support vector machine and the Textblob package. In the consolidated result, it was observed that there were 84.14% positive messages, 12.32% negative and finally with 3.54% of neutral messages.