FAKE NEWS DETECTION USING STACKED ENSEMBLE OF CLASSIFIERS
Thorne, James, Chen, Mingjie, Myrianthous, Giorgos, Pu, Jiashu, Wang, Xiaoxuan, Vlachos, Andreas · International Research Journal of Modernization in Engineering Technology and Science · 2023
Fake news detection is most important and has an immense impact to our society.On one hand, it will enhance the user experience on the online social media platform and will also save a lot of time of users that they might spend on fake news otherwise.It is less time-consuming, easily conveyance socially relevant news, possibility for obtaining various perspectives of a single news and is updated every minute.On the other hand, news is manipulated by various networking sites based on private opinions or interest.The rapid increase of fake news on social media and Internet is deceiving people to an extent which needs to be stopped.In this paper the use of machine learning techniques is used to detect fake news using Naive Bayes classification, Random forest, and Support vector machine model to predict whether news on social media will labelled as REAL or FAKE.The Stacking Ensemble classifiers is a concept in machine learning model, where multiple models is trained to solve the same problem and uniting them into a single system to get better results.This predicts probability that given statement is real or fake and performs the appropriate classification.