Analisis Sentimen Komentar Netizen di Twitter terhadap Keputusan Mahkamah Konstitusi pada Hasil Pemilihan Presiden 2024 Menggunakan Algoritma Naïve Bayes

Abstract

This research is focused on assessing the public opinion of netizens on Twitter regarding the Constitutional Court's decision on the results of the 2024 Presidential Election by utilizing the Naïve Bayes classification algorithm. Twitter is the main social media platform that many people use to voice their opinions, including on political issues. Through the Naïve Bayes classification method, public opinion is divided into two main sentiments: positive and negative. This research began with the collection of comment data through the scraping process, then continued with the pre-processing stages of data which included case folding, tokenizing, normalization, stopword removal, and stemming. The processed data is then manually labeled to form training data. The Naïve Bayes model was trained using the training data, then tested using test data to evaluate the performance of the classification model. The results of the evaluation showed that the model had an accuracy rate of 90%, with precision and recall values in the positive class of 83% each. These findings show that the Naïve Bayes algorithm can effectively classify netizens' sentiments against the Constitutional Court's ruling. In addition, the classification results also show that netizens' opinions tend to be divided, with a slightly higher proportion of negative sentiments compared to positive sentiments. This study also enriches the methods used in digital sentiment analysis, especially in understanding public responses to political issues that develop on social media. The results of this study are expected to be a reference in data-based decision-making on public opinion, especially in the realm of public policy, political communication, and digital information management. Going forward, similar research could be further developed with different algorithms or with a wider scope of data to get a more comprehensive picture.