Computer Spots Fakers Better Than People Do

Rambo Tribble (1273454) writes "Using sophisticated pattern matching software, researchers have had substantially better success with a computer, than was obtained with human subjects, in spotting faked facial expressions of pain. [Original, paywalled article in Current Biology] From the Reuters piece: '... human subjects did no better than chance — about 50 percent ...', 'The computer was right 85 percent of the time.'"

Comments

In 3 .. 2 .. 1

[OzPeter]

Outlawed by FIFA!

Re:In 3 .. 2 .. 1

[ericloewe]

But, but... The referee's humanity is part of the game! It's not right to question his judgement with gadgets!

Re:In 3 .. 2 .. 1

[Marginal Coward]

I am imagining how they produced the images of faces of people where were actually in pain.

They turned the dial on the Milgram Experiment up to 11. Or so it seems...

It wasn't the computer

[fullback]

The people who programmed "the computer" were better.

Re:It wasn't the computer

[Trepidity]

I'd say it's a mixture of the two. The computer can't discriminate these facial features without people to program it, but the people can't discriminate these facial features on their own, either, because we aren't good at applying this kind of analysis ourselves (even if we can come up with what it ought to be). The existence of a computer isn't enough, and the existence of the people is also insufficient, to carry out the task. So I'd call it a collaborative activity.

Re:It wasn't the computer

[ColdWetDog]

That would be an interesting test. I agree, 25 random volunteers really isn't all that high of a bar. Do the same with some experienced clinicians and see what happens.

Moreover, pain is a pretty complex issue - there is acute, nocioceptive (pain receptor) pain - as in the test. Chronic pain is quite a bit different. Visceral pain (from nerve fibers in the abdomen) is different still.

I think that a computer assisted study of emotions has the potential for improving human performance in decoding those emotions, but this is clearly in it's infancy. I don't think there will be an app for that in the near future (a real one, that is).

Re:It wasn't the computer

[Trepidity]

I'd say the computer is pretty intelligent. For one, it's better at recognizing facial expressions than people are! ;-)

I mean, if you hired a textile worker, nobody would object if you talked about the worker being "good" or "bad" at sewing, even though they didn't design the sewing machinery and aren't exhibiting any particular creativity, but rather are just following instructions.

Re:It wasn't the computer

[Artifakt]

There's a good precedent for your argument that this is a question of instinctual skill vrs trained skill, but it doesn't take anything like a billion examples to train a person in the example I'm considering. A very common way to teach health care personnel to recognize Fetal Alchohol Syndrome is to give them an album with several hundred photos of people in various life stages, all suffering from FAS. This method has worked since the time when the photos were black and white, and in fact, using color shots or video footage doesn't seem to have any impact on success or the number of examples needed. Once someone is trained that way, the success percentage is in the very high 90s, and stays that way, at least for a typical crreer. Similar methods are used for other diseases, for example most people have learned to spot Down's syndrome from just a few examples, but where the syndrome produces only some of the usual appearance effects, spotting the 'borderline cases' with high accuracy can be taught this same way, usually taking about 15 minutes.

Hollywood

[AlphaWolf_HK]

Perhaps watching faked facial expressions on TV and whatnot has dulled our ability to distinguish them?

Re:Hollywood

[Artifakt]

In the 1970's there was a book called "Four Arguments for the Abolition of Television", or something like that. One of the arguments was the limited image quality of the 512 line scan made even very poorly faked emotions very hard to distinguish from the real thing, and so children who got their learning examples of human expressions from TV would have a hard time telling who was really feeling emotions or just faking them. The author also claimed that emotions such as Rage, Fear, and Strong Suffering would come through better than subtler emotions such as Boredom, Fondness or Compassion, so TV scripts would come to emphasize those emotions which at least somewhat worked and ignore the rest. Perhaps there's something to these ideas.

Empathy, inexperience

[Dan East]

Computers do not feel empathy. Perhaps the empathy humans feel when seeing others in pain overrides any minor inconsistencies in the visual side of things. Further, humans do not "analyze" one others' faces to identify an emotion. We see faces (even if it's the same ones over and over) so many times that it's just an automatic, generalized classification. If people often faked painful facial features, and there was some strong motivation to identify that fact, then I'm sure we would be more adept at it. The only time I can think of in a real-world setting where people fake painful facial features is in jest or to be funny or "sarcastic" in some way (not counting football (aka soccer) matches). Thus the overall context totally reveals the expression to be fake and thus visual side of things is just an afterthought.

WHAT WERE THE VARIOUS CONTROL GROUPS?

[mosel-saar-ruwer]

What did they use to teach the computer?

Did they torture a bunch of undergraduates with cattle prods, and then load the photographs of the undergraduates screaming in pain into their great big giant neural network of "true positives"?

Versus photographs of other undergraduates, deeply immersed in their favorite pornography websites, as their "true negatives"*?

And who were the human beings who were competing against the computers?

Random joe sixpacks plucked right off of the street, or folks like Military Medics and Civilian EMTs and Oncology Nurses and Trauma Surgeons, who have a lifetime of experience watching true pain in their patients and who know exactly what it looks like?

*And God only knows how they would categorize the undergraduates who like to hang out at sites like kink.com, watching naked people being tortured with cattle prods.

Pain versus pleasure

[swb]

I often wonder how well our medical establishment has studied the euphoric effect of opiates and how they contribute to or even in some cases surpass the functional pain relief.

I had a traumatic hand injury two months ago which involved a partial amputation of one of my fingers. I experience a lot of "pins and needles" nerve stimulation and some false limb pain (pressure or stabbing-type sensation where I have no finger) and generalized fatigue in my hand. I take small (5 mg) doses of oxycodone once or twice a day and I "feel better" but without necessarily specific reduction of any one kind of pain -- I still feel it, but it bothers me less.

I don't think it's an addiction response; some days I take zero and don't feel any classic withdrawal symptom I've ever read about. But I sometimes wonder if the pain reduction is really the result of interaction with my pain, or because the eurphoric nature of the drug just makes me feel overall better, raising my psychological tolerance of pain without actually reducing the pain itself.

I wonder philosophically if it "matters" -- if the drug produces a euphoria that allows me to tolerate the pain, is that somehow less legitimate than some functional reduction of pain that may be the drug's principal purpose? What is the effect and what is the side effect? Os is it just a question of dose versus ancillary risks (whether it's addiction or some other more organic disturbance, eg, skin rash, etc).