April Fools’ Day can be amusing or annoying depending on which side of the pranks you stand, but the peculiar tradition might also hold some serious utility in helping to tackle the scourge of fake news, new research reveals.
Come Monday morning, the internet will be awash with April Fools hoaxes set up by brands, some media outlets and individuals on social media.
Confusion and confoundment will ensue, as well as smiles (and a good measure of relief when people realize there are no sharks in Lake Ontario).
When the dust settles on all the hilarious practical jokes, however, researchers will be left with a treasure trove of data that could improve our ability to detect malicious fake news stories.
In a new study, Edward Dearden and Alistair Baron of Lancaster University in the U.K. describe how they used data about the structural and stylistic similarities between April Fools and fake news stories to design algorithms to spot fake news online.
“April Fools hoaxes are very useful because they provide us with a verifiable body of deceptive texts that give us an opportunity to find out about the linguistic techniques used when an author writes something fictitious disguised as a factual account,” said Dearden, lead author of the study, titled “Fool’s Errand: Looking at April Fools Hoaxes as Disinformation through the Lens of Deception and Humour.”
“By looking at the language used in April Fools and comparing them with fake news stories we can get a better picture of the kinds of language used by authors of disinformation.”
WATCH: From chocolate Whoppers to ‘smartphoneshoe’ – companies get creative with April Fools’ Day pranks (Apr. 1, 2018)
The researchers scrutinized over 500 April Fools articles published on more than 370 websites since 2005 to construct a comprehensive linguistic profile of the prototypical April Fools story.
They then compared their April Fools dataset with a dataset of fake news stories put together by a different research team and found a number of similarities between the two.
Compared to genuine news, April Fools hoax stories and fake news stories both tend to be shorter in length and easier to read, and use more first-person pronouns. Details that are crucial to news reporting, such as dates, times, names and places, were also found to be used less frequently in April Fools and fake news stories.
The researchers also used their data to build an algorithm that was then put to work identifying whether stories were real news, fake news or April Fools pranks.
The algorithm achieved 75 per cent accuracy in identifying April Fools stories and 72 per cent in identifying fake news.
When the algorithm was trained on April Fools stories as a baseline and then asked to identify fake news, it recorded an accuracy of over 65 per cent.
“Looking at details and complexities within a text are crucial when trying to determine if an article is a hoax,” said Baron. “Although there are many differences, our results suggest that April Fools and fake news articles share some similar features, mostly involving structural complexity.
“Our findings suggest that there are certain features in common between different forms of disinformation and exploring these similarities may provide important insights for future research into deceptive news stories.”