Mark Zuckerberg has so far downplayed the significance of the spread of false information on Facebook and its effect on the 2016 election results. Stating that fake news is but a tiny fraction of what’s shared on the popular social networking site, he has openly denied such propaganda lies to have much of an impact.
“The idea that fake news on Facebook, which is a very small amount of the content, influenced the election in any way I think is a pretty crazy idea,” Zuckerberg was quoted as saying during a technology trends conference in California.
Zuckerberg would later announce in a post that while Facebook is dealing with hoaxes and fake news, the task has remained to be a challenge for the company.
For four college students, however, creating an algorithm to determine real news from lies is really not that difficult.
At a hackathon at Princeton University, a group of students representing different schools crafted a newsfeed authenticity checker algorithm in the form of Chrome browser extension.
The project, dubbed as “FiB: Stop living a lie,” was completed in just 36 hours.
Subscribe to
NextShark's Newsletter
A daily dose of Asian America's essential stories, in under 5 minutes.
Get our collection of Asian America's most essential stories to your inbox daily for free.
Unsure? Check out our Newsletter Archive.
The group consisted of Nabanita De, a second year Masters in Computer Science student at UMass Amherst, Anant Goel a freshmen at Purdue University, Mark Craft, a sophomore at the University of Illinois Urbana-Champaign, and Catherine Craft, also a sophomore at Urbana-Champaign.
De explained to Business Insider how their algorithm works:
“It classifies every post, be it pictures (Twitter snapshots), adult content pictures, fake links, malware links, fake news links as verified or non-verified using artificial intelligence.
“For links, we take into account the website’s reputation, also query it against malware and phishing websites database and also take the content, search it on Google/Bing, retrieve searches with high confidence and summarize that link and show to the user. For pictures like Twitter snapshots, we convert the image to text, use the usernames mentioned in the tweet, to get all tweets of the user and check if current tweet was ever posted by the user.”
“For links, we take into account the website’s reputation, also query it against malware and phishing websites database and also take the content, search it on Google/Bing, retrieve searches with high confidence and summarize that link and show to the user. For pictures like Twitter snapshots, we convert the image to text, use the usernames mentioned in the tweet, to get all tweets of the user and check if current tweet was ever posted by the user.”
The plug-in automatically indicates whether the story is verified or not via a little tag in the corner.
For fake stories, it would note that the story is “not verified,” while real stories are tagged as “verified.”
Currently released as an open source project, the students’ extension can be downloaded by any developer for installation and further improvements.
Of course, having a working Chrome plug-in that labels fake news is one thing, and having everyone willingly install it is another. While FiB is a great way to start, it would still be most ideal to have Facebook ultimately identify and remove fake articles by itself.
Incidentally, Facebook was one of the companies which sponsored the hackathon event.
To try the extension follow the instructions:
Download the files here. Then while on Chrome, go to Settings -> Extensions, and enable “developer mode”. Click “load unpacked extension” and select the “extension” folder that you downloaded.
