Abstract

The primary goal of this study is to compare the analysis results of sentiment analysis using three different machine learning models: Naïve Bayes, Support Vector Machine (SVM), and Random Forest. The raw dataset used for this study is sourced from the Google Play Scraper API, which is then preprocessed to ensure quality and accuracy of feature extraction. Once preprocessed, the machine divides the dataset for training and testing using the 80:20 rule. The results of this comparison provide insights into the strengths and weaknesses of each algorithm in the context of sentiment analysis of user reviews. This study aims to inform practitioners about the most effective techniques for extracting actionable insights from user-generated content on digital platforms. The evaluation shows that the Naïve Bayes model achieved the highest accuracy of 81%, followed by the SVM model with 80%, and the Random Forest model with 76%. These findings highlight the Naïve Bayes model as the most accurate for sentiment analysis in this context, with all models demonstrating robust performance.

Details

Title
Sentiment Analysis on User Reviews of Threads Applications in Indonesia
Author
Madyatmadja, Evaristus Didik  VIAFID ORCID Logo  ; Candra, Hubert  VIAFID ORCID Logo  ; Jovan Nathaniel  VIAFID ORCID Logo  ; Miguel Roland Jonathan  VIAFID ORCID Logo  ; Rudy  VIAFID ORCID Logo 
Pages
1165-1171
Publication year
2024
Publication date
Aug 2024
Publisher
International Information and Engineering Technology Association (IIETA)
ISSN
12696935
e-ISSN
21167087
Source type
Scholarly Journal
Language of publication
French; English
ProQuest document ID
3107679231
Copyright
© 2024. This work is published under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.