PUBLIC OPINION ON COVID 19 REGULATION IN INDONESIA: PREDICTION USING NAÏVE BAYES AND TERM WEIGHTING TF-IDF

Abstract

There are many public responses about the implementation of government policies related to Covid-19. Some have positive and negative opinion, especially on the official social media portal of the government twitter where people are free to argue. This study aims to find out the opinion of sentiment analysis on Twitter in the implementation of government policies related to Covid-19 so as to classify public opinion. Several stages in the process of analyzing public sentiment are taken from the tweet data. The first step is to do the data mining process to get the tweets that will be analyzed later. Furthermore, the process of cleaning tweet data and equalizing tweet data into lowercase. After that perform the basic word search process of the tweet and calculate the frequency of its appearance. Then calculate using the naïve bayes method and determine the sentiment classification of the tweet. The results showed that public sentiment related to covid-19 prevention in Indonesia is neutral. The performance of the application shows an Accuracy value of 76.7%