Disinformation: Analysis and Identification

The paper aims to answer the two following questions: 1-“Can we automatically and accurately classify a news article as containing disinformation?” 2- “What characteristics of disinformation differentiate it from other types of benign information?” The paper concludes that fact checking is needed for credibility checks and that style based classifiers are not enough. It also finds that natural language inference automating that is used to automate/ semi-automate fact checking processes, such as web app and FactFinder, are a development in the right direction.