Algorithm for Detecting Polarity of Opinions in University Students Comments on Their Teachers Performance

Sentiment analysis is a text classification task within the area of natural language processing whose objective is to detect the polarity (positive, negative or neutral) of an opinion given by a certain user. Knowing the opinion that a person has toward a product or service is of great help for deci...

Full description

Bibliographic Details
Authors: Silva, Jesús, Sanchez Montero, Edgardo Rafael, Cabrera, Danelys, Chacon, Ramon, Vargas, Martin, Pineda Lezama, Omar Bonerge, Orellano, Nataly
Format: article
Status:Versión aceptada para publicación
Publication Date:2021
Country:Colombia
Institution:Corporación Universidad de la Costa
Repository:Repositorio REDICUC
Language:Spanish
OAI Identifier:oai:repositorio.cuc.edu.co:11323/7694
Online Access:https://hdl.handle.net/11323/7694
https://doi.org/10.1007/978-981-15-7234-0_90
https://repositorio.cuc.edu.co/
Access Level:Open access
Keyword:Analysis of polarity
Opinion mining
Supervised classification
Description
Summary:Sentiment analysis is a text classification task within the area of natural language processing whose objective is to detect the polarity (positive, negative or neutral) of an opinion given by a certain user. Knowing the opinion that a person has toward a product or service is of great help for decision making, since it allows, among other things, potential consumers to verify the quality of the product or service before using it. This paper presents the results obtained from the automatic identification of the polarity of comments emitted by university students in a survey corresponding to the performance of their professors. In order to carry out the identification of the polarity of comments, a technique based on automatic learning is used, which initially makes a manual labeling of the comments and then these results allow to feed different learning algorithms in order to create the classification models that will be used to automatically label new comments, and thus determine their polarity as positive or negative.