<![CDATA[The spread of hoax news on digital platforms is increasingly becoming a serious concern as it can trigger mass disinformation and potentially cause widespread social disruption. Platform X, as one of the most widely used social media, is often used as a means of spreading unverified information. Therefore, an automatic detection system is needed that is able to identify hoax news effectively and efficiently. This research aims to build a text-based hoax news classification model by applying a text mining approach and the Support Vector Machine (SVM) algorithm. The dataset used comes from Platform X and has gone through a series of preprocessing stages, including case folding, tokenization, stopword removal, and stemming. The feature extraction process is performed using the Term Frequency-Inverse Document Frequency (TF-IDF) method to convert text into numerical representations that can be processed by the SVM algorithm. The built model is then evaluated using several performance metrics, such as accuracy, precision, recall, and F1-score. The evaluation results show that the SVM model is able to classify hoax news with 83.2% accuracy, 81.5% precision, 84.7% recall, and 83.0% F1-score. This finding shows that the SVM algorithm is quite reliable in detecting text-based hoax news and has the potential to be implemented as a solution to mitigate the spread of false information on digital platforms more broadly.]]>
Copyrights © 2025
