<![CDATA[AbstractOnline conversations among netizens play an important role in forming collective opinions and views about important events, including judicial decisions such as those taken by the Constitutional Court (MK). This research explores sentiment analysis of the Constitutional Court’s decisions, especially in the context of the presidential election, using the Support Vector Machine (SVM), Logistic Regression, and Naive Bayes algorithms. Previous studies on public sentiment toward the Constitutional Court’s decision provide a basis. Still, this research focuses on a different context, analysing sentiment toward the Constitutional Court’s decision in the 2024 presidential election dispute. This study adopts an experimental methodology, involving several key stages such as data collection through Twitter web scraping, labelling, pre-processing, TF-IDF weighting, and algorithm testing. Evaluation using a confusion matrix shows comparable accuracy among SVM, Logistic Regression, and Naive Bayes, with SVM and Logistic Regression demonstrating superior precision and F1 scores. Negative sentiment carries greater weight than neutral and positive sentiment, highlighting potential social tensions and the need for effective communication and deeper analysis to understand the root causes of negativity. The SVM and logistic regression algorithms have proven effective in understanding public sentiment towards the Constitutional Court’s decisions in a political context, providing valuable insights for understanding the dynamics of public opinion.]]>
Copyrights © 2024
