Abstract
In recent years, disinformation and “fake news” have been spreading throughout the internet at rates never seen before. This has created the need for fact-checking organizations, groups that seek out claims and comment on their veracity, to spawn worldwide to stem the tide of misinformation. However, even with the many human-powered fact-checking organizations that are currently in operation, disinformation continues to run rampant throughout the Web, and the existing organizations are unable to keep up. This paper discusses in detail recent advances in computer science to use natural language processing to automate fact checking. It follows the entire process of automated fact checking using natural language processing, from detecting claims to fact checking to outputting results. In summary, automated fact checking works well in some cases, though generalized fact checking still needs improvement prior to widespread use.
Highlights
Fact checking has been becoming more popular since the early 20000 s, it has grown in popularity greatly in recent years
This paper examines how Natural Language Processing (NLP) is used to fact check claims in written text, from the start of defining claims and determining those worthy of verification, to how parsed claims are verified against facts that are known to be true
There are approximately 160 fact checking organizations globally [3], and several online based fact checking applications, false information continues to spread on the internet
Summary
Fact checking has been becoming more popular since the early 20000 s, it has grown in popularity greatly in recent years. With the rise of social media and “fake news” spreading throughout the web [2], fast and accurate fact checking is more imperative than ever This is difficult, as the claims that need to be checked are written in human languages. A simple query for the web-based fact-checker of “From 2016–2020 Donald Trump was President of the United States of America” returned no results that indicate that the query is true, most of the results being related to his age. This is an undesirable result for a simple query. This paper examines how NLP is used to fact check claims in written text, from the start of defining claims and determining those worthy of verification, to how parsed claims are verified against facts that are known to be true
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
