Fake news websites could be identified by the partners that provide their video streaming and advertising, research shows.
The new approach could help search engines and social media giants, such as Facebook and Twitter, to flag untrustworthy articles more rapidly and prevent their misleading content going viral.
Fake news stories and conspiracy theories have proliferated online during the coronavirus pandemic, from alleged cures to claims the virus is caused by 5G technology.
Ram Gopal, Professor of Information Systems Management at Warwick Business School, said:
“The US Presidential Elections in 2016 highlighted the significant harm that fake news can do, potentially impacting election outcomes and undermining democratic institutions.
“These concerns have multiplied during the coronavirus pandemic and fake news has resulted in an untold number of deaths from misleading and harmful information.
“It is vital that we use all the tools at our disposal to combat the spread of fake news and the huge damage it does.”
Flagging fake news stories typically involves humans or Artificial Intelligence (AI) scanning individual articles for misleading information.
This is difficult as articles can be quickly changed to defeat the algorithms designed to catch them.
Now researchers at Warwick Business School have found fake news and clickbait websites tend to use the same supply chain partners to provide key components, such as advertising platforms.
While fake news websites can disguise their text and images to appear real, they cannot conceal which partners they use, as these can be easily identified using browsing tools.
Professor Gopal said: “Trying to identify fake news articles is a cat and mouse game, because the content can be quickly changed to defeat the algorithms searching for them.
“To detect fake news effectively we need strong markers that are difficult to hide or fudge.
“A website’s choice of third-party partners exposes the essence of what the website does and how it achieves that. A tiger cannot hide its stripes.”
The researchers compared more than 450 top news websites, as listed by alexa.com, with 50 fake news websites and 50 clickbait sites identified by the Harvard University Library.
They identified 115 significant third parties that were only used by trustworthy sites and seven that were only used by untrustworthy platforms. These markers helped identify untrustworthy websites more rapidly and efficiently, with an accuracy of 94%.
The findings were published in the paper, Real or not? Identifying untrustworthy news websites using third-party partnerships, in the journal ACM Transactions on Management Information Systems.
Professor Gopal said: “It is not a case of these markers replacing traditional content analysis. The two approaches can complement each other.
“Content can be scrutinised more closely, with a lower threshold for action, if it originates from a website that our markers classify as illegitimate. Integrating the two approaches could result in more accurate and more robust detection mechanisms.”
