“ClaimBuster”

Reporters’ Lab students are fact-checking North Carolina politicians

Student journalists and computer scientists find claims and report articles for the N.C. Fact-Checking Project

By Catherine Clabby – November 20, 2018 | Print this article

Duke Reporters’ Lab students expanded vital political journalism during a historic midterm campaign season this fall with the North Carolina Fact-Checking Project.

Five student journalists reviewed thousands of statements that hundreds of North Carolina candidates vying for state and federal offices made online and during public appearances. They collected newsy and checkable claims from what amounted to a firehose of political claims presented as fact.

Duke computer science undergraduates with the Duke Tech & Check Cooperative applied custom-made bots and the ClaimBuster algorithm to scrape and sort checkable political claims from hundreds of political Twitter feeds.

Editors and reporters then selected claims the students had logged for most of the project’s 30 plus  fact-checks and six summary articles that the News and Observer and PolitiFact North Carolina published between August and November.

Duke senior Bill McCarthy

Duke senior Bill McCarthy was part of the four-reporter team on the project, which the North Carolina Local News Lab Fund supported to expand local fact-checking during the 2018 midterms and beyond in a large, politically divided and politically active state.

“Publishing content in any which way is exciting when you know it has some value to voters, to democracy,” said McCarthy, who interned at PolitiFact in Washington, D.C. last summer. “It was especially exciting to get so many fact-checks published in so little time.”

Reporters found politicians and political groups often did not stick with the facts during a campaign election season that that fielded an unusually large number of candidates statewide and a surge in voter turnout.

The N.C. Fact-Checking Project produces nonpartisan journalism

NC GOP falsely ties dozens of Democrats to single-payer health care plan,” read one project fact-check headline. “Democrat falsely links newly-appointed Republican to health care bill,” noted another.  The fact-check “Ad misleads about NC governors opposing constitutional amendments” set the record straight about some Democratic-leaning claims about six proposed amendments to the state constitution.

And on and on.

Digging for the Truth

Work in the lab was painstaking. Five sophomores filled weekday shifts to scour hundreds of campaign websites, social media feeds, Facebook and Google political ads, televised debates, campaign mailers and whatever else they could put their eyes on. Often they recorded one politician’s attacks on an opponent that might, or might not, be true.

Students scanned political chatter from all over the state, tracking competitive state and congressional races most closely. The resulting journalism was news that people could use as they were assessing candidates for the General Assembly and U.S. Congress as well as six proposed amendments to the state constitution.

The Reporters’ Lab launched a mini news service to share each fact-checking article with hundreds of newsrooms across the state for free.

One of more than 30 N.C. Fact-Checking Project articles

The Charlotte Observer, a McClatchy newspaper like the N&O, published several checks. So did smaller publications such as Asheville’s Citizen-Times  and the Greensboro News and Record. Newsweek cited  a fact-check report by the N&O’s Rashaan Ayesh and Andy Specht about a fake photo of Justice Kavanaugh’s accuser, Christine Blasey Ford, shared by the chairman of the Cabarrus County GOP, which WRAL referenced in a roundup.

Project fact-checks influenced political discourse directly too. Candidates referred to project fact-checks in campaign messaging on social media and even in campaign ads. Democrat Dan McCready, who lost a close race against Republican Mark Marris in District 9, used project fact-checks in two campaign ads promoted on Facebook and in multiple posts on his Facebook campaign page, for instance.

While N&O reporter Andy Specht was reporting a deceptive ad from the Stop Deceptive Amendments political committee, the group announced plans to change it.

The fact-checking project will restart in January, when North Carolina’s reconfigured General Assembly opens its first 2019 session.

 

Back to top

Lessons learned from fact-checking 2018 midterm campaigns

After monitoring political messaging, students see the need for accountability journalism more than ever

By Catherine Clabby – November 20, 2018 | Print this article

Five Duke undergraduates monitored thousands of political claims this semester during a heated midterm campaign season for the N.C. Fact-Checking Project.

That work helped expand nonpartisan political coverage in a politically divided state with lots of contested races for state and federal seats this fall. The effort resumes in January when the project turns its attention to a newly configured North Carolina General Assembly.

Three student journalists who tackled this work with fellow sophomores Alex Johnson and Sydney McKinney reflect on what they’ve learned so far.

Lizzie Bond

Lizzie Bond: After spending the summer working in two congressional offices on Capitol Hill, I began my work in the Reporters’ Lab and on the N.C. Fact-Checking Project with first-hand knowledge of how carefully elected officials and their staff craft statements in press releases and on social media. This practice derives from a fear of distorting the meaning or connotation of their words. And in this social media age where so many outlets are available for sharing information and for people to consume it, this fear runs deep.

Yet, it took me discovering one candidate for my perspective to shift on the value of our work with the N.C. Fact-Checking Project. That candidate, Peter Boykin, proved to be a much more complicated figure than any other politician whose social media we monitored. The Republican running to represent Greensboro’s District 58 in the General Assembly, Boykin is the founder of “Gays for Trump,” a former online pornography actor, a Pro-Trump radio show host, and an already controversial, far-right online figure with tens of thousands of followers. Pouring through Boykin’s nearly dozen social media accounts, I came across everything from innocuous self-recorded music video covers to contentious content, like hostile characterizations of liberals and advocacy of conspiracy theories, like one regarding the Las Vegas mass shooting which he pushed with little to no corroborating evidence.

When contrasting Boykin’s posts on both his personal and campaign social media accounts with the more cautious and mild statements from other North Carolina candidates, I realized that catching untruthful claims has a more ambitious goal that simply detecting and reporting falsehoods. By reminding politicians that they should be accountable to the facts in the first place, fact-checking strives to improve their commitment to truth-telling. The push away from truth and decency in our politics and toward sharp antagonism and even alternate realities becomes normalized when Republican leaders support candidates like Boykin as simply another GOP candidate. The N.C. Fact-Checking Project is helping to revive truth and decency in North Carolina’s politics and to challenge the conspiracy theories and pants-on-fire campaign claims that threaten the self-regulating, healthy political society we seek.

Ryan Williams

Ryan Williams: I came into the Reporters’ Lab with relatively little journalism experience. I spent the past summer working on social media outreach & strategy at a non-profit where I drafted tweets and wrote the occasional blog post. But I’d never tuned into writing with the immense brevity of political messages during an election season. The N.C. Fact-Checking Project showed me the importance of people who not only find the facts are but who report them in a nonpartisan, objective manner that is accessible to an average person.

Following the 2016 election, some people blamed journalists and pollsters for creating false expectations about who would win the presidency. I was one of those critics. In the two and a half months I spent fact-checking North Carolina’s midterm races, I learned how hard fact-checkers and reporters work. My fellow fact-checkers and I compiled a litany of checkable claims made by politicians this midterm cycle. Those claims, along with claims found by the automated claim-finding algorithm ClaimBuster were raw material for many fact-checks of some of North Carolina hottest races. Those checks were made available for voters ahead of polling.

Now that election day has come and gone, I am more than grateful for this experience in fact-finding and truth-reporting. Not only was I able to hone research skills, I gained a deeper understanding of the intricacies of political journalism. I can’t wait to see what claims come out of the next two years leading up to, what could be, the presidential race of my lifetime.

Jake Sheridan

Jake Sheridan: I’m a Carolina boy who has grown up on the state’s politics. I’ve worked on campaigns, went to the 2012 Democratic National Committee in my hometown of Charlotte and am the son of a long-time news reporter. I thought I knew North Carolina politics before working in the Reporter’s Lab. I was wrong.

While trying to wrap my head around the 300-plus N.C. races, I came to better understand the politics of this state. What matters in the foothills of the Piedmont, I found out, is different than what matters on the Outer Banks and in Asheville. I discovered that campaigns publicly release b-roll so that PACs can create ads for them and saw just how brutal attack ads can be. I got familiar with flooding and hog farms, strange politicians and bold campaign claims.

There was no shortage of checkable claims. That was good for me. But it’s bad for us. I trust politicians less now. The ease with which some N.C. politicians make up facts troubles me. Throughout this campaign season in North Carolina, many politicians lied, misled and told half truths. If we want democracy to work — if we want people to vote based on what is real so that they can pursue what is best for themselves and our country — we must give them truth. Fact-checking is essential to creating that truth. It has the potential to place an expectation of explanation upon politicians making claims. That’s critical for America if we want to live in a country in which our government represents our true best interests and not our best interests in an alternate reality.

 

Back to top

Duke students tackle big challenges in automated fact-checking

Trio assembled promising building blocks needed for live fact-checking

By Catherine Clabby – October 8, 2018 | Print this article

Three Duke computer science majors advanced the quest for what some computer scientists say is the Holy Grail in fact-checking this summer.

Caroline Wang, Ethan Holland and Lucas Fagan tackled major challenges to creating an automated system that can both detect factual claims while politicians speak and instantly provide fact-checks.

That required finding and customizing state-of-art computing tools that most journalists would not recognize. A collective fondness for that sort of challenge helped, a lot.

Duke junior Caroline Wang

“We had a lot of fun discussing all the different algorithms out there, and just learning what machine learning techniques had been applied to natural language processing,” said Wang, a junior also majoring in math.

Wang and her partners took on the assignment for a Data+ research project. Part of the Information Initiative at Duke, Data+ invites students and faculty to find data-driven solutions to research challenges confronting scholars on campus.

The fact-checking team convened in a Gross Hall conference from 9 am to 4 pm every weekday for 10 weeks to help each other figure out how to help achieve live fact-checking, a goal of Knight journalism professor Bill Adair and other practitioners of accountability journalism.

Their goal was to do something of a “rough cut” of end-to-end automated fact-checking: to convert a political speech to text, identify the most “checkable” sentences in the speech and then match them with previously published fact-checks.

The students concluded that Google Cloud Speech-to-Text API was the best available tool to automate audio transcriptions. They then submitted the sentences to ClaimBuster, a project at the University of Texas at Arlington that the Duke Tech & Check Cooperative uses to identify statements that merit fact-checking. ClaimBuster acted as a helpful filter that reduced the number of claims submitted to the database, which in turn reduced processing time.

They chose Google Cloud speech-to-text because it can infer where punctuation belongs, Holland said. That yields text divided into complete thoughts. Google speech-to-text also shares transcription results while it processes the audio, rather than waiting until translation is done. That speeds up how fast the new text can get moved to the next steps along a fact-checking pipeline.

Duke junior Ethan Holland

“Google will say: This is my current take and this is my current confidence that take is right. That lets you cut down on the lag,” said Holland, a junior whose second major is statistics.

Their next step was finding ways to match the claims from that speech with the database of fact-checks that came from the Lab’s Share the Facts project. (The database contains thousands of articles published by the Washington Post, FactCheck.org and PolitiFact, each checking an individual claim.)

To do that, the students adapted an algorithm that the open-source research outfit OpenAI released in June, after the students started working together. The algorithm builds on The Transformer, a new neural network computing architecture that Google researchers published just six months prior.

Duke sophomore Lucas Fagan

The architecture alters how computers organize trying to understand written language. Instead of translating a sentence word by word, The Transformer weighs the importance of each word to the meaning of every other word. Over time that system helps machines discern meaning in more and more sentences more quickly.

“It’s a lot more like learning English. You grow up hearing it and your learn it,” said Fagan, a sophomore also majoring in math.

Work by Wang, Holland and Fagan is expected to help jumpstart a Bass Connections fact-checking team that started this fall. Students on that team will continue the hunt for better strategies to find statements that are good fact-check candidates, produce pop-up fact-checks and create apps to deliver this accountability journalism to more people.

Tech & Check has $1.2 million in funding from the John S. and James L. Knight Foundation, the Facebook Journalism Project and the Craig Newmark Foundation to tackle that job.

Back to top

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

Reporters’ Lab, IFCN to host conference about automated fact-checking

The March 31-April 1 conference will showcase new research to use computational power to help fact-checkers.

By Alexios Mantzarlis – January 21, 2016 | Print this article

The Reporters’ Lab and Poynter’s International Fact-Checking Network  will host “Tech & Check”, the first conference to explore the promise and challenges of automated fact-checking.

Tech & Check, to be held March 31-April 1 at Duke University, will bring together experts from academia, journalism and the tech industry. The conference will include:

  1. Demos and presentations of current research that automates fact-checking
  2. Discussions about the institutional challenges of expanding the automated work
  3. Discussions on new areas for exploration, such as live fact-checking and automated annotation.

Research in computational fact-checking has been underway for several years, but has picked up momentum with a flurry of new projects.

While automating fact-checking entirely is still the stuff of science fiction, parts of the fact-checking process such as gathering fact-checkable claims or matching them with articles already published seem ripe for automation. As natural language processing (NLP) and other artificial intelligence tools become more sophisticated, the potential applications for fact-checking will increase.

Indeed, around the world several projects are exploring ways to make fact-checking faster and smarter through the use of technology. For example, at Duke University, an NSF-funded project uses computational power to help fact-checkers verify common claims about the voting records of members of Congress. The University of Texas-Arlington has developed a tool called ClaimBuster that can analyze long transcripts of debates and suggest sentences that could be fact-checked. At Indiana University, researchers have experimented with a tool that uses Wikipedia and knowledge networks to verify simple statements. Fact-checkers in France, Argentina, the U.K. and Italy are also doing work in this field.

The conference is made possible with support by, among others, the Park Foundation. More details will be published in the coming weeks.

Researchers and journalists interested in attending the conference should contact the International Fact-Checking Network at factchecknet@poynter.org

Back to top

Reporters’ Lab projects featured at Computation + Journalism conference

The Reporters' Lab projects on structured journalism and fact-checking were featured at the annual conference.

By Julia Donheiser – October 6, 2015 | Print this article

Two projects from the Duke Reporters’ Lab were featured at the 2015 Computation + Journalism Symposium, which was held over the weekend at Columbia University in New York.

The two-day conference included presentations about Structured Stories NYC, an experiment that involved three Duke students covering events in New York, and a separate project that is exploring new ways to automate fact-checking.

Structured Stories, which uses a unique structured journalism approach to local news, was the topic of a presentation by David Caswell, a fellow at the Reynolds Journalism Institute.

Caswell explained Structured Stories in a presentation titled the Editorial Aspects of Reporting into Structured Narratives.

Structured Stories NYC is one of the boldest experiments of structured journalism because it dices the news into short events that can be reassembled in different ways by readers. The site is designed to put readers in charge by allowing them to adjust the depth of story coverage.

On the second day of the conference, Reporters’ Lab Director Bill Adair and Naeemul Hassan, a Ph.D. student in computer science at the University of Texas-Arlington, made a presentation that Adair said was “a call to arms” to automate fact-checking. It was based on a paper called The Quest to Automate Fact-Checking that they co-authored with Chengkai Li and Mark Tremayne of the University of Texas-Arlington, Jun Yang of Duke, James Hamilton of Stanford University and Cong Yu of Google.

At the conference, Naeemul Hassan explained how the UT-Arlington computer scientists used machine learning to determine the attributes of a factual claim.
At the conference, Naeemul Hassan explained how the UT-Arlington computer scientists used machine learning to determine the attributes of a factual claim.

Adair spoke about the need for more research to achieve the “holy grail” of fully automated, instant fact-checking. Hassan gave a presentation about ClaimBuster, a tool that analyzes text and predicts which sentences are factual claims that fact-checkers might want to examine.

The Reporters’ Lab is working with computer scientists and researchers from UT-Arlington, Stanford and Google on the multi-year project to explore how computational power can assist fact-checkers.

Back to top