Paper Key : IRJ************014
Author: Ashwini Dattatray Barkale
Date Published: 15 Oct 2023
Abstract
Fake news contains misleading information that can be verified. Todays world is digital, we have advantages of the digital world but have some disadvantages too. Fake news is one of them, Anyone can easily spread fake news without knowing the impact it has on society. There are some online platforms where we can easily share fake information (Like Facebook, Instagram, Twitter, etc...). No doubt this application provides easy access to any information, but this platform gives cybercriminals a chance to spread fake news. Detecting fake news is a big challenge because it is a difficult task. So it has become important to detect fake news. Some researchers are working on the detection of fake news. Machine Learning 1 helps detect fake news, machine learning algorithms will detect fake news automatically once they are trained. There are different algorithms to detect fake news. Naive Bayes and Passive-aggressive classifiers are among the algorithms that are used to detect a fake. It is a probabilistic classifier. It is based on probability models that incorporate strong independence assumptions. It is a supervised machine learning that is widely used in classification and regression problems. This paper aims to collect the fake news dataset, apply both algorithms and find the accuracy rate in detecting fake news.