A Systematic Literature Review on the Use of Machine Learning Algorithms for Sentiment Analysis
Keywords:
Análise de Sentimentos;, Machine Learning; , NLP.Abstract
Sentiment analysis is a technique that aims to measure comments and news through artificial intelligence. The objective of this work is to investigate and map which is the most used language in the field of machine learning, as well as which NPL algorithms are most used for the application of sentiment analysis, and also to find which algorithm has the highest accuracy in this application. As a methodology, a Systematic Literature Review - RSL was elaborated, where 22 articles from the sources: Google Scholar and Scielo were analyzed. Such studies were selected based on inclusion and exclusion criteria and also via String search. It was observed that the most used language is Python, since the most used algorithms are Naive Bayes, Support Vector Machines (SVM), Random Forest and Logistic Regression. Among them, the algorithm that presented the highest accuracy was under context between SVM and Random Forest.
References
ALPAYDIN, E. Introduction to Machine Learning. MIT Press, 2010. Disponível em: <http://nuir.nkumbauniversity.ac.ug/xmlui/bitstream/handle/20.500.12383/1421/Introduction%20to%20Machine%20Learning,%20Second%20Edition%20(Adaptive%20Computation%20and%20Machine%20Learning)%20(%20PDFDrive%20).pdf?sequence=1>. Acesso em: 19/05/2023.
FREITAS, Cláudia. Sobre a construção de um léxico da afetividade para o processamento computacional do português. Revista Brasileira de Linguística Aplicada, Rio de Janeiro, v. 13, n. 4, p. 1031-1059, dez. 2013. Disponível em: <https://doi.org/10.1590/S1984-63982013005000024>. Acesso em: 19/05/2023.
KAUR, J.; SEHRA, S. S.; SEHRA, S. K. A systematic literature review of sentiment analysis techniques. International Journal of Computer Sciences and Engineering, v. 5, n. 4, p. 22-28, 2017.
KITCHENHAM, B.; CHARTERS, S. Guidelines for performing systematic literature reviews in software engineering. In: Technical report, Ver. 2.3 EBSE TechnicalReport EBSE. [S.l.]: Epidemiol. Serv. Saúde, 2007.
MÄNTYLÄ, Mika; GRAZIOTIN, Daniel; KUUTILA, Miikka. The evolution of sentiment analysis—A review of research topics, venues, and top cited papers. Computer Science Review, v. 27, p. 16-32. fev. 2018. Disponível em: <https://www.sciencedirect.com/science/article/abs/pii/S1574013717300606>. Acesso em: 21/05/2023.
PANG, Bo; LEE, Lillian. Opinion mining and sentiment analysis. Foundations and Trends in Information Retrieval, v. 2, n. 1-2, p. 1-135, jul. 2008. Disponível em: <https://www.nowpublishers.com/article/Details/INR-011>. Acesso em: 19/05/2023.
VOM BROCKE, J. et al. Reconstructing the giant: On the importance of rigour in documenting the literature search process. In: Proceedings of the 17th European Conference on Information Systems, 2009, Verona. Anais eletrônicos [...] Verona, 2009, p. 1-13. Disponível em: <https://www.researchgate.net/publication/259440652_Reconstructing_the_Giant_On_the_Importance_of_Rigour_in_Documenting_the_Literature_Search_Process>. Acesso em: 25/05/2023.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Portugues
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
A Revista Brasileira em Tecnologia da Informação utiliza a licença do Creative Commons (CC), preservando assim, a integridade dos artigos em ambiente de acesso aberto.
