Exposing a False Source of News on Social Media by using Machine Learning

Fake news, or information that seemed false with the intention of misleading the public, has been all too common in recent years. By fostering political polarization and scepticism towards the government, the dissemination of this kind of information harms societal cohesion. Human validation has become impossible due to the massive amount of news being shared on social media, leading to the development and organization of automated methods for spotting false information. To increase the appeal of their publications, fake news publishers employ a number of stylistic strategies, one of which is stirring up reader’s emotions. Our proposed methodology for exposing false news by performing feature selection method of Ensemble Bagging Classifier (EBAC), and Ensemble Boosting Classifier (EBOC), Multi-Kernel SVM(MKSVM), to experiment and choose the best fit features to obtain the sensitivity, specificity, Kappa Score, and Matthews Correlation Coefficient (MCC).