ANALISIS SENTIMEN TOKOPEDIA PADA ULASAN DI GOOGLE PLAYSTORE MENGGUNAKAN ALGORITMA NAÏVE BAYES CLASSIFIER DAN K-NEAREST NEIGHBOR

Tokopedia is one of the popular marketplaces used by e-commerce in Indonesia. The number of competing e-commerce applications makes users compare each other. Many Tokopedia users are disappointed and satisfied with the application. The purpose of this study is to assess the performance of the nave Bayes and k-nearest neighbor methods. The methods used are nave Bayes and k-nearest neighbors. This study resulted in accuracy of the nave Bayes method of 75.30% and the k-nearest neighbor method of 86.09% accuracy. Based on the accuracy value, it can be concluded that the sentiment analysis test for the Tokopedia application is better using the k-nearest neighbor algorithm.