<![CDATA[The rapid development of artificial intelligence (AI) has also had a significant impact on various aspects of life, including interactions on social media platforms such as Platform X. On this platform, users actively discuss various topics related to AI, from the benefits to the challenges it poses. Understanding how the public responds to AI technology is important for developers, researchers, and policy makers in order to design strategies that are more in line with the needs and expectations of the community. This study aims to evaluate and compare the performance of two algorithms commonly used in sentiment analysis, namely Naïve Bayes and Support Vector Machine (SVM). Data were collected through crawling techniques using Google Colab, which resulted in 9,183 entries. Before the analysis was carried out, the data went through a series of initial processing stages, including text cleaning, letter normalization, tokenization, removing frequently used words (stopword removal), and stemming to simplify words. The results of the analysis show that SVM has advantages in terms of accuracy and capability, namely 96% accuracy in handling complex data, while Naïve Bayes is faster in the computational process and efficient for large datasets, resulting in an accuracy of 84% smaller than SVM accuracy. The assessment is carried out using accuracy, precision, recall, and F1-score metrics based on the confusion matrix.]]>
Copyrights © 2025
