Sentiment Analysis of the PeduliLindungi on Google Play using the Random Forest Algorithm with SMOTE

Muhammad Rizky Pribadi, Danny Manongga, Hindriyanto Dwi Purnomo, Iwan Setyawan, Hendry Hendry

202221 citationsDOI

Abstract

At the end of 2019, the world was hit by the COVID-19 virus, which caused a pandemic. Indonesia has become one of the countries that are affected by this pandemic. To control the COVID-19 pandemic, the government has made various efforts, one of which is the use of the PeduliLindunig app. To access the PeduliLindungi app, the public can download it from Google Play. Google Play enables its users to write reviews on the apps that have been downloaded. This study aims to determine the sentiment analysis on the PeduliLindungi application on Google Play using the Random Forest Algorithm with SMOTE. Based on this study, public sentiment towards the PeduliLindungi app on Google Play tends to be negative. The Random Forest and SMOTE algorithms are used to classify sentiment in this study. The implementation of Random Forest and SMOTE resulted in 71% accuracy, 70% recall, and 70% precision.

Topics & Concepts

Random forestSentiment analysisComputer scienceDownloadGovernment (linguistics)Precision and recallCoronavirus disease 2019 (COVID-19)AlgorithmArtificial intelligenceMachine learningWorld Wide WebInfectious disease (medical specialty)MedicineLinguisticsDiseasePathologyPhilosophyData Mining and Machine Learning ApplicationsMultimedia Learning SystemsInformation Retrieval and Data Mining