International news organization Reuters revealed this week that it has been working on its own algorithm to catch breaking news on Twitter, giving journalists detailed alerts as events unfold.

According to Reg Chua, executive editor for data and innovation at Reuters, the algorithm makes life easier for journalists who are always racing to be first.

“A large part of our DNA is built on the notion of being first, so we wanted to figure out how to build systems that would give us an edge on tracking this stuff at speed and at scale,” Chua said in a recent interview with Nieman Lab. “You can throw a million humans at this stuff, but it wouldn’t solve the problem.”

According to Reuters, its algorithm not only surfaces breaking news as it happens, it also weeds out fake stories by finding reliable sources. It accomplishes this partly by focusing on the verified Twitter accounts of public figures or government organizations. In another interview with the Columbia Journalism Review, Chua explained that in the event of a bombing, the algorithm would look for trustworthy sources such as the local police station or mayor.

Chua said that the algorithm also takes other factors into account, even the way the original source tweet was written. “Amazingly enough, a tweet that is entirely in capital letters is less likely to be true,” Chua said.

Trusting news sourcing to a robot may seem a little sketchy given the recent controversy surrounding the proliferation of fake news stories circulating on sites like Facebook, but Chua noted that Reuter’s algorithm is a tool to help journalists get their work done, not to do it for them.

“With the proliferation of smartphones and social media, it means that there are lot more witnesses to a lot more events,” Chua said. “We can’t be at everything. Our tool helps shift some of the burden of witnessing and lets journalists do much more of the high value-added work.”

Photo by jeffedoe