Sentiment Analysis of TikTok Shop Prohibition Using a Random Forest and Decision Tree

Abstract

This research explores the impact of the closure of TikTok Shop by the Indonesian government on various aspects of the economy, the e-commerce industry, consumer behavior, and social media dynamics. As an e-commerce platform within the TikTok social media application, TikTok Shop has become a significant business information system that collects, provides, and stores information related to electronic buying and selling activities. Understanding the public's reaction to the closure of TikTok Shop is essential because it can influence consumer confidence, market stability, and future regulatory decisions. Public sentiment provides valuable insights into the potential economic and social consequences, guiding policymakers and businesses in making informed decisions. The closure of this platform has elicited both positive and negative reactions from the public, which are widely expressed through social media, especially Twitter. To analyze public sentiment regarding this issue, two relevant machine learning methods were used: Random Forest and Decision Trees. Random Forest is known for its efficiency in data mining and its ability to handle data imbalance in large datasets. Decision Trees offer similar accuracy and can be applied in both serial and parallel modes, depending on the available data capacity and memory. The results of this study are expected to provide in-depth insights into the implications of the closure of the TikTok Shop and the effectiveness of using machine learning algorithms in social sentiment analysis. This research yielded effective results with a 75.24% accuracy, 80.18% precision, 67.06% recall, and 73.04% F1 score.