SoylentNews is people
SoylentNews
Eye tracking can reveal an unbelievable amount of information about you:
Eye tracking technology is starting to pop up more and more, keeping track of where you're looking and how your pupils and irises are reacting for a variety of different purposes. It doesn't require particularly complex technology; a HD video camera that can watch your face is enough to collect the data.
But according to a 2020 research review, this data can divulge an extraordinary amount of information about you when it's crunched through advanced data analysis systems. "Our analysis of the literature," reads the paper's abstract, "shows that eye tracking data may implicitly contain information about a user's biometric identity, gender, age, ethnicity, body weight, personality traits, drug consumption habits, emotional state, skills and abilities, fears, interests, and sexual preferences."
That's not all; "Certain eye tracking measures," says the review, "may even reveal specific cognitive processes and can be used to diagnose various physical and mental health conditions." According to Grandview Research, "the analyzed data is used to study a myriad of psychiatric and neurological conditions, such as autism spectrum disorder (ASD), attention deficit hyperactivity disorder (ADHD), obsessive-compulsive disorder (OCD), Parkinson's, Alzheimer's, and Schizophrenia, among others."
[...] They can also track the length of fixations, rapid eye motions between fixations, smooth pursuit movements and things like the acceleration and maximum speed of your eye movements.
They can analyze your eyelids, watching how far open your eyes are, how often you're blinking and how long your eyes are staying shut when you do. They can take note of redness and see how watery or dry your eyes are through reflections. They can measure the dilation of your pupils – famously an indication of sexual interest or arousal, but also linked to drug use, fear and certain types of brain damage. They can note your eye color and iris texture.
[...] Biometric identity can be established using a combination of things. The colors and patterns in your irises, for starters, can be used almost like a fingerprint. But so can your pupil reactivity, your gaze velocity and the trajectories your eyes take when following a moving object; mechanical and brain function differences make these things unique to you.
Then there's mental workload – an area in which eye tracking sometimes performs better than an EEG. Pupil dilation can be used as a measure of task difficulty and mental effort. Your blink rate correlates with dopamine levels, signifying learning and goal-directed behavior.
[... The full study – What Does Your Gaze Reveal About You? On the Privacy Implications of Eye Tracking – is available for free at Springer Link.
(Score: 2) by pipedwho on Friday April 09 2021, @05:26AM
This starts out talking about things that might be statistically significant across a population, then goes on to extrapolate for use cases that involve individuals. Too often this is proved useless beyond pointing to 'further testing required' to get a result.
For example it may be true that there is an 87% chance that you are looking at an ad because you're interested in whatever 'hook' they provide. This is useful from a marketing standpoint, because they can select between 'hooks' that are 87% and 77%. But for an individual, this may or may not be true at all. And even for an individual where it is true, it may only be 'mostly true' and therefore can't be used to make a decision that isn't itself just a good guess.
So this type of thing might be useful for probabilistic research/marketing/etc, but is not good enough for individual assertion or diagnosis. eg. this guy is lying or this guy is gay/straight/bi, etc.