Implementasi Support Vector Machine (SVM) dan Naïve Bayes untuk Analisis Sentimen Aplikasi KAI Access

Muhammad Riky Sudrajat, Prima Dina Atika, Herlawati .

Abstract

Google Play Store is one of the platforms on Android to download an application, Google Play also provides a feature for the public to be able to provide comments/reviews of the downloaded application. Reviews of the application are in the form of perception, both positive and negative, a review of one of the applications on google play, namely the KAI access application, can be used as research material to find information. The technique that can be used for this research is sentiment analysis, the classification method that will be used for this sentiment analysis is the support vector machine and naive Bayes as a comparison to find better accuracy of the two algorithms, this research can help developers to find out the shortcomings and advantages that must be improved on the application. The results of the study using the Support Vector Machine (SVM) classification obtained an accuracy rate of 93% while using the Naïve Bayes method that was 89%. So, the Support Vector Machine method provides a higher level of accuracy than the Naïve Bayes method.

Keywords

Google Play, KAI Access, Support Vector Machine, Naïve Bayes

Full Text:

PDF

Refbacks

  • There are currently no refbacks.