Analisis Sentimen Isu Pembubaran DPR Pada Platform Tiktok Menggunakan Metode Naive Bayes dengan Optimasi Smote

The development of social media has made digital platforms a primary space for the public to express opinions on various issues, including political topics. One of the issues widely discussed is the discourse on the dissolution of the House of Representatives (DPR), which has gained significant attention on the TikTok platform. The large number of comments generated from related content produces a large amount of textual data that can be utilized to understand public perception. Therefore, this study aims to analyze public sentiment toward the issue of DPR dissolution on TikTok using the Naïve Bayes method.

The research data were collected through a scraping process of comments on TikTok videos discussing the issue of DPR dissolution, resulting in a dataset of 1.535 comments. The research stages include data preprocessing consisting of
cleaning, case folding, tokenizing, stopword removal, normalization, and stemming. The data were then labeled into three sentiment categories: positive, negative, and neutral. Furthermore, the dataset was divided into training and
testing data with a ratio of 80:20. The classification process was performed using the Naïve Bayes algorithm, while the model performance was evaluated using a confusion matrix by calculating accuracy, precision, recall, and F1-score.

The results show that the Naïve Bayes method is able to classify the sentiment of TikTok user comments with a fairly good level of accuracy. Most comments indicate negative sentiment toward the issue of DPR dissolution, reflecting
criticism and public dissatisfaction with the legislative institution. This study is expected to provide insights into public opinion on social media and serve as a reference for further research in the field of sentiment analysis.