Abstract :
The abundance of various kinds of information on the internet along with the development of the world of information and communication technology has caused a massive increase in data, one of the sources coming from social media, especially Twitter, which is currently discussion Covid-19 a lot. Reporting through Twitter media regarding the impact of the Covid-19 virus is widely discussed because it causes unrest for the public which has led to the issuance of various government policies to prevent the spread of Covid-19. Related to this, it is necessary to conduct a sentiment analysis of the text on Twitter media. In this study, sentiment analysis was carried out regarding public sentiment towards government policies during the Covid-19 pandemic in Indonesia on Twitter social media using the Naive Bayes Classifier method where the data was classified into 2 sentiment values, namely positive and negative sentiment. The data used are 300 positive tweets and 300 negative tweets, where 80% of the total data is used as training data and 20% of the data is used as test data. From the test results, with a total of 120 tweets, the results of the measurement of recall value are 93.33%, precision is 93.33%, F - Score is 93.33% and the average accuracy is 93.33%.
Keywords: sentiment analysis, covid-19, naive Bayes classification