Perbandingan Metode Naive Bayes Classifier dan Support Vector Machine pada Analisis Sentimen Twitter Topik Lifestyle

Abstract

<p><i>Technology is currently developing rapidly thanks to the widespread growth of the internet worldwide. This growth has triggered an increasing demand for diverse information, especially in textual form. One way to fulfill this information demand is through social media platforms, which enable communication and interaction among individuals. Twitter has become a popular social media platform in Indonesia, providing a space for people to express their opinions on various topics, including lifestyle. These opinions can range from positive to negative or even neutral. Sentiment analysis is needed to provide a general overview of the sentiment expressed by the Indonesian public regarding lifestyle topics. This research utilizes the Naive Bayes Classifier (NBC) and Support Vector Machine (SVM) classification methods to compare which method is most effective in analyzing sentiment towards lifestyle topics in Indonesian society. The study found that the SVM method achieved the highest accuracy of 61% and produced consistent prediction results.</i></p>