A COMPARATIVE ANALYSIS OF MACHINE LEARNING TECHNIQUES FOR FAKE NEWS DETECTION

Abstract

Differentiating between false and true information has become challenging due to the easy availability and rapid increase of data presented on social media platforms.The convenience with data may be exchanged has contributed to the fast spread of data piracy. The authenticity of social networking sites is questioned in this field where incorrect news is widely shared. We have introduced some new characteristics and evaluate the accuracy of current approaches and features for automatically detecting fake news. In addition to assessing the essential characteristics given in this study for fake news detection, we proposed a new set of features and examined the prediction effectiveness of current approaches and attributes for accurate classification of false news. and our findings show some surprising details about the utility and significance of traits in spam detection. We hope people will be able to distinguish between counterfeit and genuine news.