Fake news detection based on news content and social contexts using machine learning

Abstract

This paper presents research on detecting fake news based on news content and social context approach using machine learning. First of all, we analyze related concepts, methods of detecting fake news. Next, we model this task as a binary classification problem, representing news content and social context as feature vectors. Then we use machine learning algorithms to build the classification model. Experimental results with three machine learning algorithms: Support Vector Machine, Naive Bayes and k-Nearest Neighbors on the FakeNewsNet dataset show the effectiveness of the proposed method.