Artificial intelligence now knows your personality type just by looking at your eyes

[chubber]

Personality tests, from makeshift Facebook quizzes to serious psychological sorters, are all the rage these days. Many of these are based on the so-called "Big Five" personality traits that most contemporary personality psychologists believe make up our many varied temperaments: extraversion, agreeableness, openness, conscientiousness, and neuroticism.

Now, though, all of these tests are about to become obsolete. Pretty soon, artificial intelligence should be able to know your personality just by looking at the ways your eyes move, according to a University of South Australia press release.

Researchers at the University of South Australia, in collaboration with the University of Stuttgart, Flinders University, and the Max Planck Institute for Informatics in Germany, have developed algorithms capable of reliably identifying four of the Big Five traits in a human subject by merely tracking eye movement.

How your eyes move reveals way more about you than you ever could have imagined.

 

[Amberiat]

I went through that article hoping to find a detailed explanation of how this system actually interpreted eye movement and what I saw were the usual baseless accuracy claims, no explanation as to how it actually works.

I don't think it's impossible to make a connection between eye movement and brain activity in order to attempt predicting someones thought process (although accurately defining their personality would be very difficult even with this) but what you've linked here is nothing to get excited about, no proof nor reasoning as to how/why it works which makes it dismissable.

 

[chubber]

I went through that article hoping to find a detailed explanation of how this system actually interpreted eye movement and what I saw were the usual baseless accuracy claims, no explanation as to how it actually works.

I don't think it's impossible to make a connection between eye movement and brain activity in order to attempt predicting someones thought process (although accurately defining their personality would be very difficult even with this) but what you've linked here is nothing to get excited about, no proof nor reasoning as to how/why it works which makes it dismissable.

so you are saying you could see it not being impossible to link eye movement with brain activity and then say there is no proof of how/why it works and thus makes it dismissible?

 

[Amberiat]

so you are saying you could see it not being impossible to link eye movement with brain activity and then say there is no proof of how/why it works and thus makes it dismissible?

I'm saying I believe it could be possible to at least achieve something close to it but I don't think that this research in particular has any merit to it, it's too shallow of an attempt, but an attempt nonetheless.

 

[Icedream]

Compare it to ENIAC or early virtual reality. Technology is usually unbelievably crude when it first starts out. I'm not saying that this will certainly improve, but I am saying that it's alright if it's terrible right now, at least.

 

[Quick]

I'm saying I believe it could be possible to at least achieve something close to it but I don't think that this research in particular has any merit to it, it's too shallow of an attempt, but an attempt nonetheless.

Big data is pretty unassuming. Big data can predict when someone is about to go manic, for example. I don't think I would dismiss the claim even though the actual article is missing.