KLASIFIKASI OPINI MASYARAKAT DI TWITTER TENTANG KEBOCORAN DATA YANG TERJADI DI INDONESIA MENGGUNAKAN ALGORITMA SVM

Abstract

Personal data is sensitive and private, it can only be seen by an individual. However, as time goes by, data leaks often occur on the internet, especially in Indonesia. This data leak was busy on Twitter social media and was used as a forum for opinions regarding data leaks that occurred in Indonesia. The classification method used for this research is Support Vector Machine (SVM) with TF-IDF feature extraction. The dataset was obtained through the results of scraping Twitter and getting 5000 tweets. The dataset is manually labeled as Positive, Negative, and Neutral before entering the SVM Classification stage. And based on the results of the SVM classification, SVM produces an accuracy of 83%.