AdaBoost Ensemble Learning on top of Naive Bayes Algorithm to Discriminate Fake and Genuine News from Social Media

Abstract

There is a continuous increase in social media usage and a huge interaction takes place between users. In this context, fake news circulation or flood becomes a real thread for social media users from various perspectives. Fake news is defined as presentation of misleading information as true news. In this view, fake news is fabricated news that aims to manipulate public opinion to obtain a benefit. For example, increasing readership for profiting through clickbaits is such an aim. Social media users are manipulated through attention grabbing headlines or web-links to increase number of visitors. Therefore, an automated fake news identification model can be used by social media users to filter inadvertent web-traffic. For this goal machine learning algorithms are used in the literature as a solution for fake news problem. In machine learning literature, advancing performance of the base models is crucial. Ensemble learning is one of the key solutions to enhance model efficiency. In this work, we first generated a set of baseline machine learning algorithms and we tested them in terms of their fake news identification ability. We then made use of ensemble learning strategy to further enhance obtained results. More precisely, we obtained Naïve Bayes Multinomial classifier as the best fake news predictor having 96.74 % accuracy. We then further improved this prediction ability to 98.2 % by applying an AdaBoost ensemble learning strategy.