Skip to main content

This new fake news search engine tracks webs of web rumors

hoaxy beta screen shot 2016 12 23 at 4 51 19 pm
This Hoaxy screenshot shows how the rumors about a Hillary Clinton comment about nurses spread. Hoaxy / Screenshot
Social media can turn fake news into a tangled web — and now that web can be visualized, thanks to a new search engine for unverified news produced by researchers at Indiana University announced on Wednesday. Hoaxy is a beta program that tracks the spread of unverified stories, showing a source and how the “news” spreads over time.

A quick search of a keyword on Hoaxy turns up several different stories on the topic along with the number of related tweets, the source, and whether or not Snopes and similar resources have debunked the topic yet. Adding a checkmark next to a topic creates a visual graph of how that “news” spread.

Hoaxy puts shares on a graph — shares stem out in a web-like pattern from the original share, then new webs span off those secondary shares, creating a visual of just how the information spread.

Along with mapping out the spread of unverified news, the system tracks the number of fact checks by independent websites, including, and

The beta program comes from the Observatory on Social Media at Indiana University, stemming from work by IU Network Science Institute researcher Filippo Menczer. Several years ago, Menczer first became interested in studying the spread of fake news when he launched an experimental celebrity rumor website that explicitly stated the news was false — and just a few months later received a check for the site’s advertising revenue.

“In the past year, the influence of fake news in the U.S. has grown from a niche concern to a phenomenon with the power to sway public opinion,” Menczer said. “We’ve now seen examples of fake news inspiring real-life danger, such as the gunman who fired shots in a Washington D.C. pizza parlor in response to false claims of child trafficking.”

While the beta version currently only tracks public Twitter posts, Menczer says that understanding how fake news spreads is the first step to stop the growing influence of fake news.

Hoaxy doesn’t decide what’s true and what’s false, either — but simply tracks the spread of unverified stories. “Not all claims you can visualize on Hoaxy are false, nor are we saying that the fact-checkers are accurate 100 percent of the time,” Menczer said. “Hoaxy is a tool to observe how unverified stories and the fact-checking of those stories spreads on social media. It’s up to users to evaluate the evidence about a claim and its rebuttal.”

Editors' Recommendations

Hillary K. Grigonis
Hillary never planned on becoming a photographer—and then she was handed a camera at her first writing job and she's been…
Facebook News just expanded. Here’s how to customize your news tab
facebook news tab local launches

After launching tests to limited locations in the fall, Facebook’s dedicated news tab now houses local news for users in the U.S. Moving from testing to an official product this spring, Facebook introduced local news into the new tool. Facebook News houses journalism exclusively from a list of vetted sources while using algorithms to personalize the news that each user sees.

The Facebook News tab comes as social networks face increasing scrutiny for handling of fake news. Publishers on the new dedicated tab are selected based on “integrity signals” which Facebook developed with journalists to determine what publishers to include. The list is designed to eliminate publishers that share fake news and clickbait. The tab is partially determined by algorithms and part human curators, with journalists selecting the top stories listed in the first subsection of the new tab.

Read more
Twitter’s misinformation problem will never disappear as long as bots exist
twitter misinformation bots regulation twitterbot illustration 200603

Over the past few weeks, Twitter has been stepping up its efforts to fight misinformation and prevent it from spreading on the platform. This initiative made headlines when Twitter decided to fact-check a tweet from the President of the United States -- a move that sparked both praise and outrage, and ultimately led to an executive order from the White House.

But while Twitter has earned plaudits for calling out Trump’s verifiably false statement about mail-in ballots and voter fraud, there is no dancing around the fact that Twitter's misinformation runs much deeper than a few high-profile tweets. The most prolific and problematic peddler of misinformation on the platform is the massive army of bots that pose as average users.
Lots and lots of bots

Read more
Bot or not? A.I. looks at Twitter behavior to sort real accounts from fake
Hand holding a Twitter phone

For the past several years, there’s been heightened concern about the impact of so-called bots on platforms like Twitter. A bot in this context is a fake account synonymous with helping to spread fake news or misinformation online. But how exactly do you tell the difference between an actual human user and a bot? While clues such as the use of the basic default “egg” avatar, a username consisting of long strings of numbers, and a penchant for tweeting about certain topics might provide a few pointers, that’s hardly conclusive evidence.

That’s the challenge a recent project from a pair of researchers at the University of Southern California and University of London set out to solve. They have created an A.I. that’s designed to sort fake Twitter accounts from the real deal, based on their patterns of online behavior.

Read more