Application of Naive Bayes Classifier Method to Analyze Social Media User Sentiment Towards the Presidential Election Phase

Abstract

This research aims to analyze the sentiment of social media users towards the election. The author collected data in this research through a literature study and observation. The author uses a classification method with the Naïve Bayes Classifier Algorithm and Support Vector Machine to analyze sentiment results. Next, this research extracts word assessment features using TextBlob, which changes text into positive or negative classes. Based on the research results, after going through the text preprocessing stage of more than 15,000 tweets, 11,000 clean tweets were obtained, which were then labelled using the text blob library in Python. The labelling results show that 4,000 tweets are positive, and the rest are harmful, indicating that most social media users' sentiment towards the election is positive. Words that often appear in the positive class express support and confidence in implementing elections that are considered honest and fair. On the other hand, words in the negative class reflect negative sentiment towards implementing elections, which are considered unsuccessful and time-consuming. The Naïve Bayes method provides accuracy, precision, and recall values of 85%, 80%, and 75%. In the Support Vector Machine method, testing is carried out with three kernels (linear, RBF, and poly), where the poly kernel with the best parameter values C is ten and degree is 1 produces the highest accuracy, precision, and recall of 90%, 90%, and 85%, respectively.