<![CDATA[The development of digital technology has increased the use of social media applications such as TikTok and YouTube, resulting in a large number of user reviews on the Google Play Store. These reviews can be utilized to determine user satisfaction through sentiment analysis. This study aims to analyze the sentiment of user reviews on TikTok and YouTube applications using the Naïve Bayes and Support Vector Machine (SVM) algorithms, as well as to compare the performance of both algorithms. The research data were obtained through a web scraping process consisting of 20,000 reviews, including 10,000 TikTok reviews and 10,000 YouTube reviews. The data then underwent preprocessing, sentiment labeling, splitting into training and testing datasets, and classification using the Naïve Bayes and Support Vector Machine (SVM) algorithms. Model evaluation was conducted using a confusion matrix with accuracy, precision, recall, and F1-score as evaluation metrics. The results showed that the Naïve Bayes algorithm outperformed SVM. For the TikTok application, Naïve Bayes achieved an accuracy of 80.30%, precision of 80.20%, recall of 80.30%, and F1-score of 80.20%, while SVM achieved an accuracy of 78.70%, precision of 78.60%, recall of 78.70%, and F1-score of 78.50%. For the YouTube application, Naïve Bayes achieved an accuracy of 78.40%, precision of 78.00%, recall of 78.40%, and F1-score of 77.90%, while SVM achieved an accuracy of 77.50%, precision of 77.20%, recall of 77.50%, and F1-score of 76.70%. Based on these results, the Naïve Bayes algorithm demonstrated better performance in classifying user review sentiments on TikTok and YouTube applications.]]>
Copyrights © 2026
