Identifying Hoaxes in Fake Spotter using XG Boost Machine Learning based Classification Method

Social media has greatly streamlined communication in recent years which uses network, shares information, and keep up with current events. Many posts on social media are questionable and meant to deceive. There is a lot of fake news everywhere and online fake news could cause serious societal issues. It is crucial for us to identify false and misleading internet content. Technically, it is hard for us to differentiate between real and fake information. The development and sharing of content have been made easier by social media platforms, leading to a significant amount that must be examined. Information on the internet is diverse making this process difficult. In order to assess the reliability and purpose of statements, humans and machines must work together. Manually identifying fake news is challenging, and it can only be done when the individual doing the identification has extensive understanding of news. Therefore, there is a need for machine learning classifiers that can identify the false news automatically. The main goal is to measure the accuracy of deceptive detection utilizing various machine learning algorithms. Several machine learning (ML) techniques, such as Decision Trees (DT), Random Forest (RF), Logistic Regression (LR), Passive Aggressive Classifier (PAC), Extra Trees Classifier (ETC) and boosting algorithms were employed on datasets to determine if the content is authentic or untrue in order to identify hoaxes on different platforms for online networking sites.