<![CDATA[The development of information and communication technology has accelerated the spread of information through digital media, yet has also increased the risk of fake news and disinformation that can influence public opinion and national stability. This study aims to classify hoax and factual news using the Support Vector Machine (SVM) method. Hoax data were obtained from the TurnBackHoax dataset, while factual data were collected from the CNN Indonesia online news portal. The data were processed through text preprocessing stages, followed by feature weighting using Term Frequency–Inverse Document Frequency (TF-IDF). The model was evaluated using a confusion matrix with accuracy, precision, recall, and F1-score metrics. The results show that the SVM model achieved an accuracy of 96.43%, indicating excellent classification performance in distinguishing hoax from factual news. This method proves effective and has the potential to support early detection of disinformation in Indonesia. Keywords: news classification; hoax; Support Vector Machine; TF-IDF; disinformation detection ]]>
Copyrights © 2026
