ANALISIS SENTIMEN TWITTER MENGGUNAKAN ALGORITMA NAIVES BAYES CLASSIFIER (Studi Kasus Jasa Transportasi Online Gojek dan Grab pada Twitter)

In this digital era, social media has become one of the places or media for expression and opinion on various topics. Social media is a new set of communication and collaboration tools, enabling many types of interactions that were previously impossible for ordinary people. Indonesia is a good place to share ideas, a library of ideas, a place to gather information, stimulate ideas, or see what friends are doing. Twitter is one of the social media where users can search for certain topics and discuss current issues. Sentiment analysis is a type of natural language processing to find out people's moods about products. or a specific topic. The Naïve Bayes Classifier is a statistical classification method that can predict the probability of class membership, such as the probability that a given sample belongs to a particular class. Naïve Bayes Classifier is a classification method rooted in Bayes theorem, which predicts future opportunities based on previous experience. many studies have developed existing methods into new high-accuracy methods.This method will be used in this study to classify data taken from Twitter and the data will be classified into positive class and negative class. Naïve Bayes Classifier is a classification method rooted in Bayes theorem, which predicts future opportunities based on previous experience. such as the probability that a given sample belongs to a particular class. This method will be used in this study to classify data taken from Twitter and the data will be classified into positive class and negative class. This method will be used in this study to classify data taken from Twitter and the data will be classified into positive class and negative class. \ Twitter netizens' assessment of online services such as gojek and grab in the past 1 year (30 September 2021 - 29 September 2022). And it is known that the final score or value in the form of accuracy from the Naive Bayes algorithm results in insufficient performance in classifying sentiment labels because the accuracy value generated in this algorithm is 0.84