N-gram and Kernel Performance Using Support Vector Machine Algorithm for Fake News Detection System

Abstract

The modern technological advancements have made it simpler for fake news to circulate online. The researchers have developed several strategies to overcome this obstacle, including text classification, distribution network analysis, and human-machine hybrid methods. The most common method is text categorization, and many researchers offer deep learning and machine learning models as remedies. An Indonesian language fake news detection system based on news headlines was developed in this work using the Support Vector Machine (SVM) kernel and n-gram. The objective of this research is to identify the model that produces the best performance outcomes. The system deployment on the web will employ the model that produces the greatest outcomes. According to the research findings, the linear kernel SVM algorithm produces the best results, with an accuracy value of 0.974. Furthermore, the bigram feature used in the development of a classification model does not increase the precision of fake news identification in Indonesian. Utilizing the unigram function yields the most accurate results.

Keywords

• fake news
• kernel
• n-gram
• support vector machine
• text classification