Menus Subscribe Search

Follow us


Quick Studies

robo eyes

(Photo: ARTEMENKO VALENTYN/Shutterstock

Computers See Human Pain Better Than You

• March 21, 2014 • 1:20 PM

(Photo: ARTEMENKO VALENTYN/Shutterstock

A new study reveals that expression recognition software performs way better than humans at discriminating between real and fake emotion.

Computers can kick our butts at math, logic, and chess—by now, that’s a given. But reading emotions, most of us probably would like to believe, is a skill reserved for humans. Isn’t that a big part of what separates us from machines in the first place?

Well, not anymore. In a study published this week in Current Biology, researchers led by the University of California-San Diego’s Marian Bartlett pitted humans against computers in a battle to see who could best distinguish between genuine and faked facial expressions of pain. We lost, by a lot.

In the experiment, more than 150 participants were shown short videos of the faces of people who either dunked their arms in ice water or pretended to dunk their arms in ice water. The group was asked to gauge the authenticity of each pained reaction, and succeeded in weeding out the fakers from the true sufferers only 51.9 percent of the time—no more accurate than if they simply had left their guess to chance.

Faked-Pain-imageWhich video screenshot shows this woman experiencing actual pain? (Photo: University of California-San Diego) (Answer: B)

Next, the researchers showed the same videos to computers with special expression recognition software. The computers’ accuracy? Eighty-five percent.

That the humans performed so poorly actually is no surprise. Scientists have known for a while that even trained physicians can’t reliably differentiate between real and faked pain expressions.

But the computers’ results were unprecedented. Bartlett and her colleagues call the success of the recognition software “a significant milestone for machine vision systems.” While computers’ logical prowess has been demonstrated for decades, the machines “have significantly underperformed compared to humans at perceptual processes, rarely reaching even the level of a human child.”

The secret to computers’ improvement, the researchers explain, is their newly refined ability to exploit one of our own physiological quirks. Two distinct motor pathways control our facial movements, one for the expressions we choose to make and the other for expressions we make spontaneously in reaction to something. When we attempt to mimic an emotion like pain, the former pathway directs our features based on what it estimates that emotion is supposed to look like, without any definitive blueprint to follow. Inevitably, small differences crop up that are too subtle for the naked eye, but not the digital lens.

“The single most predictive feature of falsified expressions of pain is the dynamics of the mouth opening,” which alone can account for 72 percent of the accuracy, the researchers write.

It’s not hard to spin the computers’ emotional savviness as a harbinger of machine domination, but Bartlett and her colleagues prefer to look at more practical applications. These include preventing insurance fraud by catching patients who lie to their doctors, improving homeland security, and exposing students who only pretend to pay attention in class.

Heightened surveillance of our expressions could have big costs, too, of course. The software, like many new technologies, leaves us with a big question: How much do we really want computers to know?

Paul Bisceglio
Editorial Fellow Paul Bisceglio was previously an editorial intern at Smithsonian magazine and a staff reporter at Manhattan Media. He is a graduate of Haverford College and completed a Fulbright scholarship at the University of Warwick in Coventry, United Kingdom. Follow him on Twitter @PaulBisceglio.

More From Paul Bisceglio

A weekly roundup of the best of Pacific Standard and PSmag.com, delivered straight to your inbox.

Recent Posts

October 31 • 8:00 AM

Who Wants a Cute Congressman?

You probably do—even if you won’t admit it. In politics, looks aren’t everything, but they’re definitely something.


October 31 • 7:00 AM

Why Scientists Make Promises They Can’t Keep

A research proposal that is totally upfront about the uncertainty of the scientific process and its potential benefits might never pass governmental muster.


October 31 • 6:12 AM

The Psychology of a Horror Movie Fan

Scientists have tried to figure out the appeal of axe murderers and creepy dolls, but it mostly remains a spooky mystery.


October 31 • 4:00 AM

The Power of Third Person Plural on Support for Public Policies

Researchers find citizens react differently to policy proposals when they’re framed as impacting “people,” as opposed to “you.”


October 30 • 4:00 PM

I Should Have Told My High School Students About My Struggle With Drinking

As a teacher, my students confided in me about many harrowing aspects of their lives. I never crossed the line and shared my biggest problem with them—but now I wish I had.


October 30 • 2:00 PM

How Dark Money Got a Mining Company Everything It Wanted

An accidentally released court filing reveals how one company secretly gave money to a non-profit that helped get favorable mining legislation passed.


October 30 • 12:00 PM

The Halloween Industrial Complex

The scariest thing about Halloween might be just how seriously we take it. For this week’s holiday, Americans of all ages will spend more than $5 billion on disposable costumes and bite-size candy.


October 30 • 10:00 AM

Sky’s the Limit: The Case for Selling Air Rights

Lower taxes and debt, increased revenue for the city, and a much better use of space in already dense environments: Selling air rights and encouraging upward growth seem like no-brainers, but NIMBY resistance and philosophical barriers remain.


October 30 • 9:00 AM

Cycles of Fear and Bias in the Criminal Justice System

Exploring the psychological roots of racial disparity in U.S. prisons.


October 30 • 8:00 AM

How Do You Make a Living, Email Newsletter Writer?

Noah Davis talks to Wait But Why writer Tim Urban about the newsletter concept, the research process, and escaping “money-flushing toilet” status.



October 30 • 6:00 AM

Dreamers of the Carbon-Free Dream

Can California go full-renewable?


October 30 • 5:08 AM

We’re Not So Great at Rejecting Each Other

And it’s probably something we should work on.


October 30 • 4:00 AM

He’s Definitely a Liberal—Just Check Out His Brain Scan

New research finds political ideology can be easily determined by examining how one’s brain reacts to disgusting images.


October 29 • 4:00 PM

Should We Prosecute Climate Change Protesters Who Break the Law?

A conversation with Bristol County, Massachusetts, District Attorney Sam Sutter, who dropped steep charges against two climate change protesters.


October 29 • 2:23 PM

Innovation Geography: The Beginning of the End for Silicon Valley

Will a lack of affordable housing hinder the growth of creative start-ups?


October 29 • 2:00 PM

Trapped in the Tobacco Debt Trap

A refinance of Niagara County, New York’s tobacco bonds was good news—but for investors, not taxpayers.


October 29 • 12:00 PM

Purity and Self-Mutilation in Thailand

During the nine-day Phuket Vegetarian Festival, a group of chosen ones known as the mah song torture themselves in order to redirect bad luck and misfortune away from their communities and ensure a year of prosperity.


October 29 • 10:00 AM

Can Proposition 47 Solve California’s Problem With Mass Incarceration?

Reducing penalties for low-level felonies could be the next step in rolling back draconian sentencing laws and addressing the criminal justice system’s long legacy of racism.


October 29 • 9:00 AM

Chronic Fatigue Syndrome and the Brain

Neuroscientists find less—but potentially stronger—white matter in the brains of patients with CFS.


October 29 • 8:00 AM

America’s Bathrooms Are a Total Failure

No matter which American bathroom is crowned in this year’s America’s Best Restroom contest, it will still have a host of terrible flaws.



October 29 • 6:00 AM

Tell Us What You Really Think

In politics, are we always just looking out for No. 1?


October 29 • 4:00 AM

Racial Resentment Drives Tea Party Membership

New research finds a strong link between tea party membership and anti-black feelings.


October 28 • 4:00 PM

The New Health App on Apple’s iOS 8 Is Literally Dangerous

Design isn’t neutral. Design is a picture of inequality, of systems of power, and domination both subtle and not. Apple should know that.


Follow us


We’re Not So Great at Rejecting Each Other

And it's probably something we should work on.

Chronic Fatigue Syndrome and the Brain

Neuroscientists find less—but potentially stronger—white matter in the brains of patients with CFS.

Incumbents, Pray for Rain

Come next Tuesday, rain could push voters toward safer, more predictable candidates.

Could Economics Benefit From Computer Science Thinking?

Computational complexity could offer new insight into old ideas in biology and, yes, even the dismal science.

Politicians Really Aren’t Better Decision Makers

Politicians took part in a classic choice experiment but failed to do better than the rest of us.

The Big One

One town, Champlain, New York, was the source of nearly half the scams targeting small businesses in the United States last year. November/December 2014

Copyright © 2014 by Pacific Standard and The Miller-McCune Center for Research, Media, and Public Policy. All Rights Reserved.