Implementation of the c4.5 decision tree learning algorithm for sentiment analysis in e-commerce application reviews on google play store

Abstract

Objective: Forknowing the level of accuracy of the C4.5 Decision Tree Learning Algorithm in sentiment analysis of reviews of e-commerce applications on the google play store.Design/method/approach: Using C4.5 AlgorithmDecision Tree Learning.Results: This study uses a confusion matrix test with a comparison of 80% for training data and 20% for test data, where 750 is used for training data and 190 is used for test data. This test obtained an average accuracy of 92.63%, precision 69.58%, and recall 69.99%.Authenticity/state of the art: In this study using the C4.5 Algorithm Decision Tree Learningto conduct sentiment analysis of e-commerce reviews, which use the gain value to perform feature selection. There are four categories, namely display, service, access, and product. The data in this study were obtained from the google play store.