Cosmetic Shop Sentiment Analysis on TikTok Shop Using the Support Vector Machine Method

Abstract

User reviews are crucial in today's digital world for determining a product's quality. Nevertheless, these remarks are frequently disorganized and erratic, which confuses people and makes it challenging for them to make wise purchases. The erratic character of these reviews breeds uncertainty and makes determining a product's actual value more difficult. To help consumers more effectively evaluate and select products on platforms such as TikTok Shop, this study uses sentiment analysis tools. It hopes to accomplish this by improving the overall shopping experience and empowering customers to make more confident and informed selections. This research aims to assist consumers in evaluating and selecting products on TikTok Shop, an online shopping platform, by employing sentiment analysis techniques that help consumers make more informed decisions. In this study, a total of 500 comments from TikTok Shop users were collected as data. 350 comments have been set aside for training and 150 comments were set aside for testing. Data was gathered employing scraping, an automated process that makes use of the Python library's Selenium module to retrieve data from the internet. We employed the Support Vector Machine approach, an efficient machine learning tool for text classification, to assess the comments. 121 comments were categorized as having positive sentiment and 29 as having negative sentiment based on the test results. The system successfully recommended the "Ourluxbeauty" cosmetics store as a shop with many positive sentiments, indicating a recommendation level of 0.7 on the positive sentiment scale. The system's accuracy was measured using a Confusion Matrix, resulting in an accuracy rate of 78% and an inaccuracy rate of 22%. This demonstrates that the system can accurately classify comment sentiments and has significant potential for application in e-commerce practices to enhance the online shopping experience.