Analisis Sentimen Tokopedia Pada Ulasan di Google Playstore Menggunakan Algoritma Naïve Bayes Classifier dan K-Nearest Neighbor

Muhammad Farid El Firdaus (Universitas Amikom Purwokerto, Purwokerto)
Nurfaizah Nurfaizah (Universitas Amikom Purwokerto, Purwokerto)
Sarmini Sarmini (Universitas Amikom Purwokerto, Purwokerto)

JURIKOM (Jurnal Riset Komputer)
Vol 9, No 5 (2022): Oktober 2022

The growth of marketplace users in Indonesia continues to grow with one of the largest marketplaces being Tokopedia with a total download of more than 50 million. This achievement cannot be separated from the role of evaluating application performance by consumers on Google Play, this can affect other consumers' trust in the Tokopedia application. The purpose of this study is to conduct a sentiment analysis on application performance based on application user comments, where the dataset used in this study is 992 comments. The algorithms used in this research are nave Bayes algorithm and k-nearest neighbor. The results showed that the accuracy of the nave Bayes algorithm was 75.30% and the accuracy of the k-nearest neighbor algorithm was 86.09%.