Exploring User Engagement with TikTok Live Shopping: A Sentiment Analysis

The significance of sentiment analysis within text mining and natural language processing (NLP) has grown in response to the expanding accessibility of web-based applications and social media platforms for opinion dissemination. This research focuses on analyzing X (Twitter) platform data regarding user reactions to TikTok store closures in Indonesia to measure people’s interest and enthusiasm for TikTok Live Shopping. This research employs a deep learning algorithm from the RapidMiner framework to classify sentiment into positive, negative, and neutral categories. Originally known for short videos, TikTok has grown into a platform that combines entertainment and commerce through its Live Shopping. The aim of this research is to understand whether TikTok Live Shopping is an effective tool for brands to increase their presence in the market. The study concluded that although TikTok Live Shopping has potential, it is underutilized. Future research should extend the data collection period and diversify data sources to make the analysis more comprehensive. Additionally, using advanced sentiment classification methods and comparing TikTok Live Shopping with other platforms can provide deeper insights into user performance and engagement.