Predicting Color Blindness, ADD, or Learning Disorders From Game Data

An anonymous reader tips a story at VentureBeat about a company that helps game developers analyze data gathered from their games to detect cheaters. But now, the company says this data can also be used to determine other traits of the players, like whether they're minors, or whether they like to gamble. Their CEO, Lukasz Twardowski, expects such analysis will soon be able to reveal even more traits, like whether a player is color blind, has a developmental disorder, or has Alzheimer's disease. "'Games are the richest and the most meaningful form of human-computer interaction. ...By tracking how they play games, we can learn a lot about people,' Twardowski explained. Hesitatingly, he added: 'That will be a huge responsibility for us later on.' ... Academics have begun to take games more seriously, as a window into the human psyche. Games are addictive and immersive and are built to command hours of our time and attention. What better testbed for myriad psychological and medical conditions? A good game pushes us to our limits, challenging us to use both the analytical and intuitive sides of our brain.

Comments

Was this article ghost written?

[fragMasterFlash]

By Philip K. Dick?

Ender's Game

[dracocat]

Am I the only one whose first thought was of Ender's Game? In reality, I think the idea has been around for a while, and seems quite practical AND useful. To me the only surprising thing is that it hasn't been implemented yet. It seems like we should have had the technology to do something like this for a long time.

Detecting some of the problems early on can significantly help the child.

Re:Minors?

[Carnildo]

I wonder how they figured out hot to spot minors in video games???

Easy: they're the ones who swear the most in team chat.

Achievement Unlocked!

[ftsf]

You have earnt: Colourblindness!

Wear this badge of pride on your Steam Profile.

Camouflage cannot fool the colorblind

[Anonymous Coward]

Something to "bear in mind" during military style games - it'd be an easy detector, right there (most likely)... I'd also like to add that though some of the colorblind (since there are varying degrees of it) cannot see the same things "normal folks" do in "lantern tests", there are other forms of those lantern tests that show the colorblind see differently - because they can see types of those tests (whereas by way of comparison, the normal sighted cannot). I wouldn't call it "seeing the world through rose colored glasses", but, definitely seeing it differently!

Re:Camouflage cannot fool the colorblind

[Black Parrot]

I'm red-green colorblind, and it has always been a *huge* problem with games.

Also with graphs and slides. When people use color coding in graphs I often can't tell which line or bar is which. Likewise when people plot data on maps by coloring the regions - annoys the heck out of me when I'm reading something interesting and can't process the graphical data display. For slides, same problem as graphs but worse - sometimes I literally don't see one or more of the lines on a graph projected as a slide.

As for camoflage, folklore has it that during WWII a bomber was flying over the Pacific and one of the crew, colorblind, spotted an enemy ship that none of the others could see even when he pointed it out. But he convinced them to fly down for a closer look, and then they saw it.

Possibly colorblind people are more attuned to value (lightness/darkness), since that's information we can reliably process. Very often I can only spot food stains on shirts if they are darker or lighter than the material.

Re:Camouflage cannot fool the colorblind

[th3rmite]

As someone who is extremely colorblind, I have two different types, I have a tendency to stay away from games that rely on color. You are right, it is like seeing the world differently I suppose, because I have absolutely no idea what the world would look like otherwise. I imagine the world is much more bland to me than to other people.

Re:Camouflage cannot fool the colorblind

[houstonbofh]

Color is differentiated by hue and intensity. "Normal" vision is more hue than intensity. The common forms of color blindness is more intensity than hue. So camo is less effective. You can see if a portion of a car is repainted when others can not. Also, since people know this, traffic lights are not just red and green. The red is a darker intensity and the green is a lighter intensity. Even in black and white you can tell the difference.

I am color blind. Friends often take me to look at used cars. :)

Re:Camouflage cannot fool the colorblind

[Tokah]

Thank you for posting this! I helped a friend with a painting job that we didn't have time to do right. When I asked her how it came out, she said it was good mostly but sometimes looked bad when the light hit parts of the wall or at certain angles. Then I visited and it looked so awful. I had assumed she was just being nice and wanted me to feel ok about it all, but no one else seemed to notice it either. You have just cleared the whole thing up for me.

most I get but ADD?

[Riceballsan]

as someone who has some degree of ADD, I have to wonder how a video game would detect it. In general someone with ADD has less focus in many areas of life, but in many cases other activities can lead to a more solid focus, and in many cases, video games are one of those cases. Unless they intentionally make parts of the game extremely boring, I can't quite see that working.

Re:most I get but ADD?

[Sir_Sri]

With a camera you can track peoples vision. You can correlate reaction time to what's going on in game, all sorts of stuff. Games actually work very well for people with ADD because they have a constant stream of rewards keeping you focused on the task. One of the things we worry about when talking about game addiction is that it's not so much addiction as it is one of the few problems people will naturally pay attention to if they have ADD. The logical follow on to that comes from training people at various stages of brain development to behave that way (by giving them rewards), and then having games be a causation problem. Not that we know if that's actually happening yet, but that's certainly something people who do research in this area are worried about.

There are a few other tangential symptoms how quickly you get frustrated that sort of thing. Those can actually be tracked, the more sensitive the controller (if it has a gyroscope in it) the more easily you can figure out if the player is mashing buttons particularly hard, that sort of thing.

Re:most I get but ADD?

[Sir_Sri]

with any certainty

Well there's the question. If you can get 75 or 80 % accuracy in an academic setting (Which is not too hard to achieve) that may not be all that useful in a commercial environment where having a 20% error rate might completely wreck the experience.

Unfortunately all of this stuff falls under 'human testing' where I am. We wanted to do a (really short) experiment to see how different coloured icons effected a players ability to remember what an ability was. Once we realized it was something like 70 pages of paperwork and a lot of money for oversight, and this was a class project, not a research project, we basically threw our hands in the air and said fuck it, not worth it. When you are dealing with people with learning disabilities you have to worry (a lot) about anonymizing the data, making sure there's no way this could get out etc. You have to prove your experiment couldn't cause further harm to someone who has an LD etc. Honestly the rules are a bit overzealous for this kinda stuff, but that's what we have to do.

Believe it or not, the symptoms of ADHD can be quantified pretty well. You need a large data set, and you do end up with a situation where sleep deprivation mimics ADHD symptoms, so you could easily not be able to distinguish between the two. But you can track the symptoms of problems well. For colour blindness it's really really straightforward to test. Different specific problems will be more or less easy to try and detect of course.

Defeat the Ko-Dan!

[eriks]

Or how about that they have the necessary skills to man a gunstar and save the galaxy :)

Death Blossom FTW!

Re:Minors?

[Sir_Sri]

Language, hours of access, reaction time, friends (once you know one is a minor you can work backwards).

Kids also have certain stages of development with language and reasoning, and they will suffer from difficulties with particular challenges in sequence.

While not my research area, I'm AI development, there are people in my research group who have looked at this problem. Even with machine learning, if you have a reasonably accurate training set you can blindly pick out certain things.

Even basic stuff. Do they have a credit card in their name? If not then you don't have proof of course, but you can start to combine with other factors and start seeing a pattern of child like behaviour.

Kids will also like some much more childish games in addition to adult ones (so an 11 year old might play a game like 'campers!' just released for the iphone, and grand theft auto, whereas a 30 year old would only play grand theft auto).

Disturbing

[girlintraining]

The problem isn't that this personal information can be sniffed out... it's that there are no laws preventing its misuse...

Dear Customer,
We regret to inform you that your medical insurance rates will be increasing by 7.35% effective immediately due to a undiagnosed, but now pre-existing condition. Also, your car insurance will be going up by 3%, and your doctor wants to schedule a psychiatric evaluation.

Sincerely,
Your Gaming Company
P.S. We detected that you have an addictive personality and tend to be forgetful. Your monthly renewal fee has been adjusted upwards accordingly. You won't remember this.

Re:Disturbing

[houstonbofh]

So will gaming companies be subject to HIPA now?

Re:Minors?

[Lehk228]

def isUserAChild(user):
    if (len(re.findall("faggot|fag|homo",allChatMessages(user)))*3>len(allChatMessages(user)):
         return true
    return false