<![CDATA[products, where user comments often provide valuable feedback. This research aims to analyze the sentiment of user comments on Indonesian-language Beauty Vlogger channels, specifically regarding reviews of powder and skincare products, to identify the positive or negative responses that emerge. Utilizing the Support Vector Machine (SVM) method as a classification algorithm and TF-IDF as a weighting technique, this study involves 1,000 comments divided into 800 training data and 200 testing data. The data is analyzed through the text preprocessing stage, followed by sentiment classification using SVM. The results indicate that the model achieved an accuracy of 97%, with a precision of 98% and a recall of 96%, demonstrating that SVM is effective in identifying sentiment in user comments. This system is expected to provide in-depth insights for Beauty Vloggers in understanding opinions regarding powder and skincare products, as well as contribute to the development of similar applications in other industries]]>
Copyrights © 2025
