Klasifikasi Sentimen Opini Metaverse dari Twitter Menggunakan Algoritma Support Vector Machine

Abstract

With the increasing use of Twitter, a real-time social media platform, it has become one of the places or spaces for people to express their opinions about the metaverse. Therefore, the development of a program capable of classifying tweets based on their opinions into positive, negative, and neutral categories is necessary. In conducting sentiment analysis, the Support Vector Machine (SVM) algorithm is used for classification. The results of this research, through testing using a confusion matrix, yield an accuracy rate of 0.83 or 83%, indicating the level of agreement between the model's predictions and the actual outcomes. Additionally, a precision of 0.93 or 93% is obtained, which shows the model's ability to accurately identify positive, negative, and neutral sentiments in tweets, and a recall of 0.83 or 83%, which describes the model's capability to find and classify accurately.