Klasifikasi Ulasan Aplikasi TikTok Menggunakan Algoritma K-Nearest Neighbor dan Chi Square

Abstract

TikTok application has achieved extraordinary popularity among users around the world, which has been downloaded by more than 500 million users with 16 million reviews and received a rating of 4.4 out of 5 on the Google Play Store. In this study, we will analyze user sentiment towards the TikTok application reviews. These reviews can be a benchmark for users to find out information about user experience and become a race for application developers to improve performance or quality. For that we need a method to describe the reviewer efficiently so that it is easier to understand the reviewer. In this study, the authors used a comparison of the KNN algorithm with the effect of feature selection to carry out the classification. Classification of application reviews into two classes, positive reviews, and negative reviews. In this classification, it is found that using Chi Square feature selection can produce the highest accuracy, with k = 9 value of 86.22% whereas without Chi Square feature selection it only produces the highest accuracy with k = 11 value of 77.04%.