ANALYSIS OF INDONESIAN PUBLIC SENTIMENT TOWARDS TIKTOK SHOP USING NAIVE BAYES AND RANDOM FOREST METHODS

Abstract

This study aims to determine the sentiment of the Indonesian people towards TikTok Shop using sentiment analysis. This study uses a quantitative approach by collecting 2340 sentiment data taken from Twitter social media. For sentiment analysis, two machine learning algorithms are applied, namely Naïve Bayes and Random. The first stage is data collection through crawling from Twitter. Then the selection of relevant attributes for analysis is carried out. And the raw data is converted into structured data that is ready to be analyzed. Furthermore, data labeling and classification model development are carried out. Finally, an evaluation of model performance is carried out using and k-fold cross validation to ensure the accuracy of the analysis results. The results show that the Naïve Bayes algorithm produces an accuracy of 66.41%, while the Random Forest algorithm produces an accuracy of 57.81%. Thus, Naïve Bayes is superior with an accuracy difference of 8.60% compared to Random Forest. Sentiment analysis with Naïve Bayes produces 375 positive sentiments and 346 negative sentiments. These results indicate that the public has diverse views on TikTok Shop. This study is expected to provide valuable insights for TikTok Shop managers to improve the quality of their services based on user feedback. In addition, the results of this study can also be a reference for further research in the field of sentiment analysis and e-commerce. Keywords: Tiktok Shop, Social Media, Sentiment Analysis, Digital Commerce, Marketing Strategy.