This new AI can track 200 eye movements to determine your personality traits

  • German scientists have developed software that can detect character traits through eyetracking, according to a new study.
  • Using over 200 physical behaviours, such as the frequency with which subjects blinked, the researchers established connections between eye movements and personality traits.
  • It’s been suggested that the technology could eventually be developed to assist those with autism to gauge their peers’ emotions and responses.

Anyone who’s seen “2001: A Space Odyseey” will already be familiar with that nagging fear that Artificial Intelligence will one day become so intelligent, it will simply turn on us — but computer scientists from Saarbrücken and Stuttgart don’t seem at all phased at the prospect.

According to a new study, they’ve developed software that can recognise personality traits through eye-tracking.

“There are already some studies in the field of emotion recognition through facial expression analysis. But this is the first time we’ve managed to establish personal traits,” said Andreas Bulling in an interview with Business Insider.

Head of the research group “Perceptual User Interfaces” at the Max Planck Institute for Computer Science at Saarland University in Saarbrücken, he joined forces with scientists from Stuttgart and psychologists from the University of South Australia to develop software that can recognise character traits through eye-tracking.

The study found personal traits are more stable than emotions

As part of their research, the scientists had 50 students, all of whom were equipped with eye-trackers recording their eye movements, walk across their campus for around 10 minutes and buy something from one of the campus shops.

Subjects were asked to complete questionnaires commonly used to evaluate people’s personality traits.

Using over 200 markers such as the frequency with which subjects blinked, how long they focused on something, and to what extent their pupils dilated, the researchers managed to establish which traits were associated with which eye movements.

While there are currently no plans for Bulling’s team to get involved in robotics, he says there’s a lot of scope for the software to be used in the field. Sergei Karpukhin/Reuters

Using the data obtained from the study, the scientists developed “decision trees” for various personality traits, after which the software was able to recognise those characteristics specified. Through eye tracking, the software can “see” whether someone is conscientious, sociable, tolerant, and even to what extent they might be emotionally unstable. It can also pick up on how inquisitive someone is.

However, what makes the AI even more special is that it doesn’t require updates; rather, it’s a “machine-learning” piece of software.

“It’s novel in itself that this kind of software works at all,” said Bulling. Emotions can vary from one situation to the next so they’re often changing regularly and quickly; character traits, however, are very stable.

“Initially, it wasn’t clear that it was possible to assess character traits from eye movements,” said the expert.

The next step is to improve the software’s performance: The experts want to focus on analysing body language too. The experts have expressed that, while it isn’t their own vision to incorporate the software into hardware, there is great scope for the application of this software in the robotics field.

The software could even assist those with autism

Eyetracking glasses equipped with this software could assist those struggling with autism to better understand their peers’ behaviour and emotions. Shutterstock

“Like anything, what we’ve made can be used for both good and bad,” said Bulling, but he hopes the software will lead to better and more authentic interaction between man and machine.

Just as an example, the eye-tracking software could eventually be installed in cars, which would then be able to recognise whether drivers are more willing to take risks or not.

If the software is sufficiently developed, it could even be used to assist people with autism: With eye-tracking glasses, those struggling to gauge their peers’ reactions and feelings could better understand others’ behaviour.

However, whether the software is used positively or negatively, Bulling said is not his responsibility: “That’s ultimately for society and the politicians to decide.”

Author: Katharina Maß
Image Credit

Eye eye! DeepMind teams up with doctors to ogle eyeballs for illness

AI can help speed up diagnosis and seldom gets it wrong

AI can help ophthalmologists diagnose more than 50 common eye diseases from retinal scans, according to a paper published in Nature Medicine on Monday.


Researchers from DeepMind, University College London (UCL), and Moorfields Eye Hospital in London, have developed a system based on two neural networks that analyses 3D optical coherence tomography scans.

First, a convolutional neural network processes the scanned image and converts it into a tissue map, detailing its anatomy and features. This is then fed into a second convolutional neural network that analyses the eye tissues in detail to diagnose diseases and recommend treatment plans, such as if the patient needs to be book a further appointment with an ophthalmologist or not.

It can, apparently, recommend the right referral procedure with 94 per cent accuracy for over 50 diseases such as age-related macular degeneration, a common condition amongst the elderly.

Unlike other systems, this one doesn’t have to be trained on millions of different scans, according to the paper. “Automated diagnosis of a medical image, even for a single disease, faces two main challenges: technical variations in the imaging process (different devices, noise, ageing of the components and so on), and patient-to-patient variability in pathological manifestations of disease.”

“Existing deep learning approaches tried to deal with all combinations of these variations using a single end-to-end black-box network, thus typically requiring millions of labeled scans.”

By mapping the eye scans into different components first, the system simplifies and reduces the amount of variation in eye scans making it easier to analyze. Other systems need to be exposed to more images so that it can generalize better. This one, however, required only 14,884 scans for training from 7,621 patients.


Machine learning tools will help speed up the process of diagnoses and treatment for patients, said Pearse Keane, co-author of the paper and an ophthalmologist at Moorfields Eye Hospital and a clinician scientist at UCL.

“The number of eye scans we’re performing is growing at a pace much faster than human experts are able to interpret them. The AI technology we’re developing is designed to prioritise patients who need to be seen and treated urgently by a doctor or eye care professional. If we can diagnose and treat eye conditions early, it gives us the best chance of saving people’s sight. With further research it could lead to greater consistency and quality of care for patients with eye problems in the future.”

Here at Dollar Destruction, we endeavour to bring to you the latest, most important news from around the globe. We scan the web looking for the most valuable content and dish it right up for you! The content of this article was provided by the source referenced. Dollar Destruction does not endorse and is not responsible for or liable for any content, accuracy, quality, advertising, products or other materials on this page. As always, we encourage you to perform your own research!

Author: Katyanna Quach
Image Credit

Don’t forget to join our facebook page for Crypto, Business & Technology news delivered to you daily.