Author : Pallavi Petkar and Dr. S. S. Sonawan

The extensive spread of fake news (low quality news with intentionally false information) has the potential for extremely negative impacts on individuals, society and particular in the political world. Therefore, fake news detection on social media has recently become an emerging research which is attracting tremendous attention. The Fake News Challenge was encourage for development of machine learning- based classification system that perform stance detection that is to identify whether a particular news headline is related or is unrelated to a particular news article to allow journalists and others to easily investigate possible instance of fake news. This is technically challenging for several reasons. Use of various social media tools, content is easily generated and quickly spread, which lead to a large volume of content to analyze. Online information is very wide spread, which cover a large number of subjects, which contributes complexity to this task. More attention needed on real time detection as rumors and bad news are particularly hard to fix once they spread. The application of machine learning techniques are explored for the detection of fake news that come from non- reputable sources which mislead real news stories. The purpose of the work is to come up with a solution that can be utilized by users to detect and filter out sites containing false and misleading information.

Keywords: Fake news detector, Stance detection, Fake news categorization, content modeling, Machine learning, Social media, online fake news, twitter.