<![CDATA[Sentiment analysis, or opinion mining, is a method used to identify public opinions expressed in textual form on social media platforms. This approach is useful for understanding public responses to a particular phenomenon without the need for conventional survey methods. This study focuses on sentiment analysis of user comments on viral TikTok videos categorized under the For You Page (FYP). The dataset was obtained through a comment crawling process, resulting in 12,494 comments, which were then processed through preprocessing stages including case folding, text normalization, stopword removal, and stemming. Sentiment classification was performed using the Naïve Bayes method with Term Frequency–Inverse Document Frequency (TF-IDF) weighting and two sentiment classes, namely positive and negative. The data were split using an 80% training and 20% testing scheme. Experimental results show that the proposed method achieved a best accuracy of 90%, demonstrating that the combination of comprehensive preprocessing and TF-IDF weighting effectively improves the performance of sentiment classification on comments from TikTok FYP videos.]]>
Copyrights © 2026
