ANALISIS SENTIMEN PADA TWITTER TERKAIT NEW NORMAL DENGAN METODE NAÏVE BAYES CLASSIFIER

Abstract

The rapid development of information technology has made it easy for the
public to access information quickly, one of which is on social media. Social
media, especially Twitter, is now a very popular communication tool among
internet users. With social media twitter, there is information data that can be
processed into sentiment analysis. This study aims to classify positive and
negative public sentiments on twitter related to the new normal during the
pandemic. The method used in this research is the Naïve Bayes Classifier and
the output of this system is visualization in the form of wordcloud. The data
used were 3000 tweets consisting of 2409 positive tweets and 591 negative
tweets. Sentiment analysis using the Naïve Bayes Classifier with TF-IDF
weighting produces an average accuracy value of 87.33%.  
Keywords: New Normal, Naïve Bayes Classifier