Analisis Sentimen Ulasan Aplikasi Identitas Kependudukan Digital Pada Play Store Menggunakan Metode Naïve Bayes

Abstract

One of the government's new innovations is the implementation of Digital Population Identity which is to bring transformation in the way people prove their own identity, making it easier, safer, and more efficient in various contexts of everyday life. It is known that on October 20, 2023 the Digital Population Identity application only received 3.3 stars from 32.7 thousand reviews, this shows that the application still has not reached the maximum level of satisfaction in serving the needs of the community. Therefore, sentiment analysis of user reviews is needed to gain deeper insight into how people respond to this application, so this research aims to obtain sentiment data from the Digital Population Identity application on the Play Store in the form of reviews from users and the results of the analysis can be used as evaluation material for application developers. Data collection is done using the scrapping method through Google Colab as many as 1000 reviews whose results will be labeled negative and positive. Then the data will be cleaned and simplified through preprocessing, and will be classified with the Naïve Bayes algorithm with 90% test data and 10% training data for each iteration. The classification results are then calculated performance with confusion matrix and obtained an accuracy value of 82.23%, precission of 76.08%, and recall of 94.02%.