Four University students solve Facebook’s Fake News problem in just 36 hours!

Background

There have been tons of the incessant criticisms leveled against Facebook after the just ended US election for allowing the influential platform to be used as a channel for disseminating propaganda lies paraded as news stories.

The effect of feeding the Social Network’s users with false, unchecked news during the electioneering period was so obnoxious that the outgoing US President, Barrack Obama, described Facebook as “a dust of cloud nonsense”.

Mark Zuckerberg, CEO of Facebook has debunked these allegations as baseless. But Alyson Shontell of the Business Insider, described the CEO’s response to the allegation as “tone deaf”.

He thinks that false news is a very small percentage of Facebook’s news feed and couldn’t possible have affected the election.

However, Facebook despite trying to avoid the responsibility of presenting balanced and reliable news like a media house, has vowed to work harder to improve its ability to detect and separate misinformation from authentic ones even though it may be a ‘hard nut to crack’, Mark implies.

It may be hard for Mark but not these students

Four students; Anant Goel, a freshman in Purdue University, Nabanita De, a second-year Masters in Computer Science student in Umass Amherst, Catherine Craft-a sophomore UIUC, and Mark Craft also a sophomore, at the university of Illinois, during a hackathon at Princeton University have created an algorithm in the form of chrome browser extension in less than two days, 36 hours to be precise!!

The project was dubbed “FiB: Stop living a lie”. The extension has been released as an open source project and this is how news feed authenticity filter works;

It classifies every post- pictures, adult content pictures, fake links, malware links, fake news links as verified or non-verified using AI (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 or Bing, retrieve searches with high confidence and summarize that link and show 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 a current tweet was ever posted by the user.”

The browser plug-in then adds a little tag in the corner that says whether or not the story is verified or not, team lead Nabanita De said.

Basically, all the plug-in does is to label a post verified or no-verified, pretty cool, huh?

The salient question is whether Facebook will get ‘chromed’ soon to inject some level of authenticity in the news feeds it supplies its users.

Facebook is one of the sponsors of the Hackathon project.