Contributions to sentiment analysis in user opinions applying artificial intelligence techniques and algorithms

Authors

Keywords:

opinion mining, sentiment analysis, supervised text classification, unsupervised text classification

Abstract

Introduction: Opinion mining is of great interest and usefulness to society and important sectors of the economy. Opinion texts are complex data where complex semantic and syntactic relationships occur due to language, which imply a challenge to consider from the computational point of view for decision-making.

Objectives: To increase the effectiveness of artificial neural training in text classification. To develop new methods that combine linguistic resources and neural models of language for polarity detection and sentiment analysis.

Methods: They are proposed a set of methods for sentiment classification (positive or negative polarity) in user opinions with unsupervised and supervised approaches. Additionally, it is introduced a new hybrid method for emotion detection in user feedback with semantic feature selection approach.

Result: We evaluated the methods on different databases for opinion analysis. The data come from news websites and their comments, British Broadcasting Corporation public databases, video comments from the Youtube platform and those proposed by SemeEval. We perform a polarity detection study on TripAdvisor comments based on the most representative places of Mexican and Cuban tourism.

Conclusions: The methods developed represent contributions that yield promising results in the state of the art for opinion analysis, being very competitive and superior in certain scenarios.

Downloads

Download data is not yet available.

Downloads

Published

2024-09-27

How to Cite

Simón-Cuevas, A. J., Toledano López, O. G., Madera Quintana, J., González Diez, H. R., Ramón Hernández, A. A., García Lorenzo, M. M., … Montañez Castelo, P. (2024). Contributions to sentiment analysis in user opinions applying artificial intelligence techniques and algorithms. Anales De La Academia De Ciencias De Cuba, 14(3), e1674. Retrieved from https://revistaccuba.sld.cu/index.php/revacc/article/view/1674

Issue

Vol. 14 No. 3: july-september 2024

Section

Technical Sciences

License

The journal Anales de la Academia de Ciencias de Cuba protects copyright, and operates with a Creative Commons License 4.0 (Creative Commons Attribution-NonCommercial License 4.0). By publishing in it, authors allow themselves to copy, reproduce, distribute, publicly communicate their work and generate derivative works, as long as the original author is cited and acknowledged. They do not allow, however, the use of the original work for commercial or lucrative purposes.

The authors authorize the publication of their writings, retaining the authorship rights, and assigning and transferring to the magazine all the rights protected by the intellectual property laws that govern in Cuba, which imply editing to disseminate the work.

Authors may establish additional agreements for the non-exclusive distribution of the version of the work published in the journal (for example, placing it in an institutional repository or publishing it in a book), with recognition of having been first published in this journal.

To learn more, see https://creativecommons.org