“Google”

At Tech & Check, some new ideas to automate fact-checking

Journalists and technologists met at Duke to dream up new ways that technology can help fact-checkers.

By Bill Adair – April 4, 2016 | Print this article

Last week, journalists and technologists gathered at Duke to dream up new ways that automation could help fact-checking.

The first Tech & Check conference, sponsored by the Duke Reporters’ Lab and Poynter’s International Fact-Checking Network, brought together about 50 journalists, students and computer scientists. The goal was to showcase existing projects and inspire new ones.

Tech and Check photo
At Tech & Check, groups of students, journalists and technologists dreamed up new ideas to automate fact-checking.

The participants included representatives of Google, IBM, NBC News, PolitiFact, Full Fact, FactCheck.org and the WRAL-TV. From the academic side, we had faculty and Ph.D students from Duke, the University of North Carolina, University of Texas-Arlington, Indiana University and the University of Michigan.

The first day featured presentations about existing projects that automate some aspect of fact-checking; the second day, attendees formed groups to conceive new projects.

The presentations showcased a wide variety of tools and research projects. Will Moy of the British site Full Fact did a demo of his claim monitoring tool that tracks the frequency of talking points, showing how often politicians said the phrase over time. Naeemul Hassan of the University of Texas at Arlington showed ClaimBuster, a project I’ve worked on, that can ingest huge amounts of text and identify factual claims that journalists might want to check.

IBM’s Ben Fletcher showed one of the company’s new projects known as Watson Angles, a tool that extracts information from Web articles and distills it into a summary that includes key players and a timeline of events. Giovanni Luca Ciampaglia, a researcher at Indiana University, showed a project that uses Wikipedia to fact-check claims.

On the second day, we focused on the future. The attendees broke into groups to come up with new ideas for research. The groups had 75 minutes to create three ideas for tools or further research. The projects showed the many ways that automation can help fact-checking.

One promising idea was dubbed “Parrot Score,” a website that could build on the approach that Full Fact is exploring for claim monitoring. It would track the frequency of claims and then calculate a score for politicians who use canned phrases more often. Tyler Dukes, a data journalist from WRAL-TV in Raleigh, N.C., said Parrot Score could be a browser extension that showed the origin of a claim and then tracked it through the political ecosystem.

Despite the focus on the digital future of journalism, we used Sharpies and a lot of Post-It notes.
Despite the focus on the digital future of journalism, we used Sharpies and a lot of Post-It notes.

Two teams proposed variations of a “Check This First” button that would allow people to verify the accuracy of a URL before they post it on Facebook or in a chat. One team dubbed it “ChatBot.” Clicking it would bring up information that would help users determine if the article was reliable.

Another team was assigned to focus on ways to improve public trust in fact-checkers. The team came up with several interesting ideas, including more transparency about the collective ratings for individual writers and editors as well as a game app that would simulate the process that journalists use to fact-check a claim. The app could improve trust by giving people an opportunity to form their own conclusions as well as demonstrating the difficult work that fact-checkers do.

Another team, which was focused on fact-checker tools, came up with some interesting ideas for tools. One would automatically detect when the journalists were examining a claim they had checked before.  Another tool would be something of a “sentence finisher” that, when a journalist began typing something such as “The unemployment rate last month…” would finish the sentence with the correct number.

The conference left me quite optimistic about the potential for more collaboration between computer scientists and fact-checkers. Things that never seemed possible, such as checking claims against the massive Wikipedia database, are increasingly doable. And many technologists are interested in doing research and creating products to help fact-checking.

Back to top

No cold pizza: Notes from a structured journalism planning session

Structured journalists meet in Cambridge to plan more events and promotion in the next year.

By Bill Adair – February 23, 2015 | Print this article

We held Friday’s meeting in a windowless conference room because that’s where we go when we discuss structured journalism. This year, our meeting was at Google’s office in Cambridge, Mass., and our host David Smydra upheld the tradition.

It’s not that we fear sunlight. It’s just a quirk of scheduling. You may recall that last year’s meeting, our first, was in a windowless room at Reuters where we munched on cold pizza. This year, we got to enjoy Google’s amazing lunch buffet.

Around the table: David, Reg Chua of Reuters, Laura and Chris Amico, the creators of Homicide Watch, and me.

The goal for our second annual structured journalism strategy session was to assess how we did in our first year and set goals for the next 12 months.

A professorial Android greeted us at Google's Cambridge office.
A professorial Android greeted us at Google’s Cambridge office.

We discussed our successes. We held well-attended panels at the International Journalism Festival in Italy and the Online News Association meeting in Chicago and we started this mailing list. We also wrote blog posts and articles, although we each felt we could have done more.

We discussed our new structured projects: Laura did a demo of a cool one she’s leading at the Boston Globe, which should be published in the next couple of weeks; Chris did a demo of two structured sites he’s built for Frontline, Ballot Watch, which follows the changes in state voting laws, and Ebola Outbreak: How the Virus Spread.

I showed two mock-ups of websites I’m building with Duke students, one to track and rate medical studies (a project now on hold because we concluded it’s too complex a subject) and one that follows cases of athletes charged with crimes. We’re calling it Rule 46, after the NHL rule on fighting.

David did demos of some Google products that can help structured journalism: Google Consumer Surveys, which can generate revenue, and Google Newsstand, which publishes free and premium articles from various sources and can display structured content in an attractive and readable form.

Reg Chua, David Smydra, Bill Adair, Laura Amico and Chris Amico.
Reg Chua, David Smydra, Bill Adair, Laura Amico and Chris Amico.

A common theme in our discussions: the need for narrative and context in structured journalism. Questions and suggestions from the group made me realize that our sports crime project needed an additional feature — articles — to help readers better understand the structured content. Readers are interested in stories, David said, and we shouldn’t “outsource how the narrative gets built” to the user.

We discussed business goals and agreed that the long-tail potential and new, innovative content formats of structured journalism projects provide different kinds of opportunities to earn revenue. It’s important for both editorial and business-side leaders to plan for revenue opportunities from the start.

We agreed to keep speaking and writing about structured journalism. We’re holding a panel titled Why Structure is the Future of Journalism at the International Journalism Festival in April and we hope to hold another one at ONA15 in Los Angeles. We’ve also started collecting a list of structured journalism projects that I’ll be publishing on the website of the Duke Reporters’ Lab. And we’d like to get this listserv more involved in developing the ideas of structured journalism and spreading the word — perhaps a larger group meeting later this year would be useful, too. (Let us know if you would be interested in that!)

We’ll be holding another planning session next year, probably at Duke. I’ll find us a windowless room.

Back to top