Real-time fact-checking is coming to live TV. But will networks use it?

factstream concept
A concept mockup of what a live fact-checking feed during the State of the Union might look like. Nate Barrett/Digital Trends

Closed captioning has been a part of our television-watching experience dating back to the 1970s; allowing anyone to follow along with what’s being said by reading subtitles at the bottom of the screen. Today, it is legally mandated that not only should home televisions sold in the U.S. contain caption decoders, but the overwhelming majority of programs — both pre-recorded and live — must offer captioning.

Could TV one day offer something similar: only not just telling viewers what is being said, but whether or not it is truthful? The TL;DR version: At least one major research project in the U.S. believes that it could.

The idea of fact checking politicians is nothing new, of course. PolitiFact, FactCheck.org, and the Washington Post‘s Fact Checker are all well known examples of systems set up to try and keep politicians honest by calling them on their exaggerations, flip-flops or even outright lies.

The Politifact Truth-O-Meter scale
Politifact’s “Truth-O-Meter” scale

What all three of these have in common, however, is that they rely on human curators to carry out their in-depth fact-checking process. That’s something that a Duke University research project is hoping to change. They are working to develop a product in time for 2020’s election year, which will allow television networks to offer real-time on-screen fact-checking whenever a politician makes a false statement.

“We’re trying to ‘close the gap’ in fact-checking,” Bill Adair, creator of PolitiFact and the Knight Professor of Journalism and Public Policy at Duke University, told Digital Trends. “Right now, if people are listening to a speech and want a fact-check, there is a gap: they have to go to a website and look it up. That takes time. We want to close that gap by providing a fact-check at the moment they hear the factual claim.”

How it works

Adair has previously overseen the creation of FactStream, a “second screen” iOS app that provides real-time push notifications to users whenever a questionable statement is made. In some cases, these direct users to a related fact check online. In others, they provides a “quick take” which fills in some of the additional facts and context. FactStream was created as part of Duke’s Tech & Check Cooperative, which has been developing automated fact-checking technology for several years.

The idea of a television version of this app is that it would offer similar functionality, but more deeply baked into the TV-viewing experience. “[It’s an automated approach which] uses voice-to-text technology, and then matches claims with related fact-checks that have been previously published,” Adair continued “When this product is built, we plan to provide the fact-checks right on the same screen as the video of the political event.”

The system would spring into action when certain phrases, which have been fact-checked before, are mentioned. According to Adair, it is likely that there would be an average of one fact check approximately every two minutes. While such a system could theoretically work in real time, networks would probably air speeches or debates on a small, one-minute delay in order to ensure smooth running of the technology.

It’s easy to see the concern over how an automated fact-checking tool could be open to bias.

A focus group was shown a demonstration of the technology in action late last year: offering demo speeches by President Trump and Barack Obama with the inserted fact checking. It was reportedly met with a favorable reaction. However, there’s still a way to go until it’s ready for prime time.

“We’re making good progress,” Adair said. “We’ve overcome some hurdles in voice-to-text and claim matching, which are the two big computational challenges. But we still need to improve the quality of our search results, and make sure we can deliver high quality matches quickly. We’re planning to have it ready for a beta test before the end of the year.”

Networks aren’t yet publicly talking about introducing a real-time automated fact-checker, although Adair insists that there is demand for such a product.

The problem with fact-checking

Would such a tool work — or find mass-approval — though? After all, we think nothing of existing automated tools like spell checks — but whether there’s a “u” in “color” is a whole lot less politically charged than today’s partisan politics.

It’s easy to see why the idea of an automated fact-checking system would appeal. Many people have argued that the spread of “fake news” was a factor in major recent political events around the world. Just like a previous tool such as the breathalyzer took a subjective problem (whether a person is capable of safely driving) and standardized it into an objective measure, so too could an A.I. fact-checker do the same for untruths.

However, it’s also easy to see why people would be worried by it — or fear that an automated tool, designed to give the impression of objectivity, could be open to bias.

Will we eventually see the rise of automated fact-checking by artificial intelligence? Should A.I. even be involved?

The jury is still out on whether increased fact-checking can sway the opinion of viewers, or make politicians more truthful. Some studies have concluded that people are more likely to vote for a candidate when fact-checking shows that they are being honest. In other cases, corrections may not have such a big impact.

Ultimately, the problem is that truth is difficult. Spotting more obvious lies is relatively low-hanging fruit, but dealing with this kind of complexity is something machines are not yet capable of. It is perfectly possible to point out what are technically true facts, but to mislead people by selective cherry-picking of statistics, leaving out information, or taking fringe cases and using them to make sweeping generalizations. These are tasks that automation is not currently equipped to handle.

“At this point, that’s beyond the capability of our automation,” Adair admitted. “We’re just trying to do voice-to-text and get high quality matches with previously published fact-checks. We are not able to write fact-checks.”

Of course, stating that A.I. will never achieve something is the siren song which has driven the industry forward. At various times, people have argued that A.I. will never beat humans at chess, fool humans into thinking they are speaking with another person, paint a picture worth selling, or win at a complex game such as Go. Time and again, artificial intelligence has proven us wrong.

Will automated fact-checking be the next example of this? We’ll have to wait and see. For now, though, this may be one task too many. But we look forward to being fact-checked.

Movies & TV

How ‘invisible’ effects brought Winnie the Pooh to life in ‘Christopher Robin’

Christopher Robin earned an Academy Award nomination for the innovative way it merged Winnie the Pooh and other imaginary characters with its human cast in postwar London. Here's how visual effects studio Framestore worked its movie magic.
Product Review

Want to see how powerful the Snapdragon 855 chip is? Just rev up the Xiaomi Mi 9

How fast do you want to go? If the answer to this is “as fast as possible,” then take a long look at the Xiaomi Mi 9. It’s one of the highest performance smartphones you can buy. It’s a real monster, and we’ve been using it.
Movies & TV

To drive its giant virtual world, Ready Player One needed a custom A.I. engine

Steven Spielberg and a visual effects team led by Roger Goyett built a new, virtual universe populated by a host of familiar characters for the Oscar-nominated Ready Player One, but they still had to maintain a powerful emotional depth in…
Movies & TV

Why First Man’s Oscar-nominated visual effects are a giant leap for filmmaking

Paul Lambert, the award-winning visual effects supervisor on First Man, reveals the innovative techniques that blended old footage with modern movie magic to make the Apollo 11 mission to the moon resonate with audiences 50 years later and…
Emerging Tech

DeepSqueak is a machine learning A.I. that reveals what rats are chatting about

Want to know what rats are squeaking about? You'd better check out DeepSqueak, the new deep learning artificial intelligence developed by researchers at the University of Washington.
Health & Fitness

Immune cell discovery takes us one step closer to a universal flu vaccine

A group of international researchers have made a discovery which could take us one step closer to the universal, one-shot flu vaccine that people around the world have been dreaming of.
Photography

NASA celebrates Earth’s incredible natural beauty with free photo book

NASA has published a fabulous new book featuring stunning imagery captured by its satellites over the years. A hardback version is available for $53, though it can also be downloaded to ebook readers for free, and enjoyed online.
Deals

This new all-in-one flashlight is a power bank, lighter, and screwdriver

The Pyyros modular flashlight can perform numerous field tasks, from hammering to starting fires. If you back it on Kickstarter now, you can score some savings on this innovative flashlight and multi-tool, but act fast: This early-bird…
Movies & TV

Hilarious new Kickstarter aims to fix Scorcese’s last scene in The Departed

A fan of The Departed and apparent hater of rat-as-symbolism imagery has launched a Kickstarter campaign to digitally erase the rodent from the end of Martin Scorsese’s 2006 movie.
Emerging Tech

Baristas beware, Bbox cafe uses robots to brew your morning coffee

Want your morning coffee and pastry prepared by robot? Bbox, a new coffee shop in downtown Berkeley, California, lets customers place their order by app and then uses automation to take care of the rest.
Emerging Tech

This ridiculous new flamethrower makes Elon Musk’s look like a cigarette lighter

The XL18 Flamethrower is a flame-shooting beast on steroids, capable of firing off bursts of flame more than 110 feet in length. The best part? You can order it over the internet today.
Emerging Tech

SpaceX just nailed its most challenging Falcon 9 rocket landing to date

If you've been following the SpaceX launch calendar, you know this week marks the first launch from Cape Canaveral in two months. We have the details on where you can watch the launch live.
Emerging Tech

Touchdown! Japan successfully lands its Hayabusa2 spacecraft on asteroid Ryugu

Japan's space agency has just completed the latest stage of its extraordinarily complex mission, successfully landing its Hayabusa2 spacecraft on an asteroid millions of miles from Earth.
Emerging Tech

Delivery drones: NASA to test advanced traffic control system for cities

Delivery drone services are edging closer as NASA prepares to demonstrate its advanced drone traffic management system, which it claims offers safe and effective control of autonomous aircraft in urban areas.