Pengembangan Aplikasi Analisis Sentimen Aplikasi Pedulilindungi Menggunakan Metode Naïve Bayes

Abstract

This study aims to build sentiment analysis application using Naïve Bayes method to analyze public view about an application called PeduliLindungi, and measure it’s accuracy by using twitter dataset. PeduliLindungi is an application developed by the government in order to track and stop Coronavirus Disease (COVID-19). The dataset used in this study is collected by using crawling method with Tweepy. Collected dataset will then go through data pre-processing and labeled by using VADER in order to separate it into positive and negative sentiments. The data will be weighted based on the frequency of its occurrence in all tweets using the TF-IDF method. The weighted data will then be classified using the Naïve Bayes method. This research used the incremental method both in model and software development. The results obtained in this study is a model with an accuracy score of 85% and an average precision, recall, and f1-score of 85%.