Comparison of Naïve Bayes Algorithm with Genetic Algorithm and Particle Swarm Optimization as Feature Selection for Sentiment Analysis Review of Digital Learning Application

Comparison of Naïve Bayes Algorithm with Genetic Algorithm and Particle Swarm Optimization as Feature Selection for Sentiment Analysis Review of Digital Learning Application

• By Ernawati, Siti; Wati, Risa; Nuris, Nuzuliarini; Marita, Lita Sari; Yulia, Eka Rini;
• Seminar Internasional
• 804

The problem examined in this study is about the user's trust in using digital

learning applications that are downloaded on playstore. Many reviews are given by the public

about the application that has been downloaded on playstore. This review is very in

uential

on their trust in using the application. The purpose of this study is to classify data according

to labels and nd out the best choice between the classication method and the proposed

selection feature as a consideration in determining the use of digital learning applications.This

study compares the classication method, the Nave Bayes algorithm and the genetic algorithm

(GA) as feature selection with the Nave Bayes algorithm classication method and the particle

swarm optimization (PSO) as feature selection to categorize the reviews in the playstore. The

experimental results show that the Nave Bayes algorithm and PSO as feature selection is the

best model between the two models proposed in this study. Reviews can be classied into

positive and negative labels well. The accuracy is 98.00%. The results of the classication are

expected to help in making decisions when going to use digital learning application.

• Katakunci -
• URL https://iopscience.iop.org/article/10.1088/1742-6596/1641/1/012040
• Penerbit Prodi Informatika, Univ. Indraprasta PGRI, Jakarta Jakarta

REFERENSI

• [1]Koncz P and Paralic J 2011 An approach to feature selection for  sentiment analysis 2011 15th IEEE Int. Conf. Intell. Eng. Syst. 357-362

  Google Scholar

• [2]
  Zhang W and Gao F 2011 An Improvement to Naive Bayes for Text Classification Elsevier 15 2160-2164

  Google Scholar

• [3]
  Vijayarani S, Ilamathi M J and Nithya M 2015 Preprocessing Techniques for Text Mining - An Overview Int. J. Comput. Sci. Commun. Networks 5 7-16

  Google Scholar

• [4]
  Ernawati S, Yulia E, Frieyadie and Samudi 2018 Implementation of The Naïve Bayes Algorithm with Feature Selection using Genetic Algorithm for Sentiment Review Analysis of Fashion Online Companies 2018 6th Int. Conf. Cyber IT Serv. Manag. Citsm 1-5

  Google Scholar

• [5]
  Ghareb A S, Bakar A A and Hamdan A R 2015 Hybrid Feature Selection Based On Enhanced Genetic Algorithm For Text Categorization Expert Syst. Appl. 49 31-47

  CrossrefGoogle Scholar

• [6]
  Syarif I 2016 Feature Selection of Network Intrusion Data using Genetic Algorithm and Particle Swarm Optimization Emit Int. J. Eng. Technol. 4 277-290

  Google Scholar

• [7]
  Ahmed B, Cha S and Tappert C 2004 Language Identification from Text Using N-gram Based Cumulative Frequency Addition Proc. Student/Faculty Res. Day, CSIS, Pace Univ. 12.1-12.8

  Google Scholar

• [8]
  Liu Y, Wang G, Chen H, Dong H, Zhu X and Wang S 2011 An Improved Particle Swarm Optimization for Feature Selection J. Bionic Eng. 8 191-200

  CrossrefGoogle Scholar

• [9]
  Shi Y and Eberhart R C 1945 Empirical Study of Particle Swarm Optimization IEEE 1945-1950

  Google Scholar

• [10]
  Günal S 2012 Hybrid feature selection for text classification Turkish J. Electr. Eng. Comput. Sci. 20 1296-1311

  Google Scholar

• [11]
  Yonghe L, Minghui L, Zeyuan Y and Lichao C 2015 Improved particle swarm optimization algorithm and its application in text feature selection Appl. Soft Comput. J. 35 629-636

  CrossrefGoogle Scholar