Advancements in technology are working towards generating computers that learn to understand human behaviour, and now, computers can interpret behaviour by examining how people use their eyes to communicate.
A team of researchers from the Max Planck Institute for Informatics has created a software system that can map out certain deductions based on the personality traits on an individual by using artificial intelligence to examine the eye movements. Humans also have a habit of forming certain subconscious beliefs based on the visual behaviour and habits of people.
In attempts to create a human-computer collaboration that is flexible, efficient, effective and social, this new software system will now have the ability of processing the eye movements of a person to calculate certain deductions, for instance, how extroverted is he/she, or how neurotic or curious they are.
Andreas Bulling, the team leader of the Perceptual User Interface research group at the Max Planck Institute for Informatics and the Cluster of Excellence at Saarland University, Saarbrücken, is reported to have explained,
Besides allowing us to perceive our surroundings, eye movements are also a window into our mind. They reveal who we are, how we feel and what we do.
Human beings are capable of interpreting and communicating through certain social signals that are sent from the eyes, and sometimes, they do so without being aware of what they’re doing. Andreas Bulling has collaborated with scientists in Australia and Stuttgart to teach this ground-breaking new skill to computers.
This basically means that eventually, robots and computers powered by artificial intelligence will be able to utilize and interpret various tools and mediums of nonverbal communication that are commonly used by human beings. This team of researchers have created a machine-based learning software system to teach computers and robots. The software works by examining eye movements, which are recorded using an eye tracker, and these movements are then used to predict the personality traits associated with the subject.
Personality traits employed by the psychologists
The researchers employed the use of artificial intelligence to develop their software with the aim of predicting four different personality traits that the psychologists have used to describe human beings. Then, the software system was capable of examining how neurotic, extroverted, conscientious and agreeable the test subjects tended to be, along with evaluating their levels of curiosity.
Andreas Bulling explains,
The predictions are not yet accurate enough for practical applications, but the system is sure to become more reliable in the future.
One of the major reasons behind Bulling’s positive outlook is that, in the future, it is highly possible to train this system with the use of comparatively larger amounts of data, accompanied with information recorded through a camera that has already been designed inside the eye tracker in order to clearly reveal what the wearer is viewing.
The data for the process of training and evaluation was obtained from 50 students, studying at the Flinders University in Australia, and the average age was put around 22 years. The eye tracker was used to record the eye movements of all the test participants as they spent around ten minutes while simply walking through their university premises, sipping on coffee, or eating something from the campus shop.
The aim was to give extra emphasis to where and how they fixed their gaze, how often did they blink their eyes, and other eye movements. Later, the researchers gave the students a set of questionnaires to fill out, these are the same questionnaires that have been used psychologists for decades while undertaking personality assessments.
Nonverbal behaviour can give robots human-like characteristics
Andreas Bulling believes that,
The knowledge about nonverbal behaviour we acquired in this study could for example be applied to robots to make their behaviour more human. Systems of this kind would then be able to communicate with humans in a much more natural fashion, which means they could be used more flexibly and efficiently.
This software can also prove to be extremely beneficial at helping people who are suffering from autism and other mental health disorders, and those who tend to face challenges while conducting nonverbal communication. Basically, it would prove useful in helping them understand the visual behaviours of the people around them, along with controlling their bizarre eye movements, for instance, avoiding the habit of staring at others for far too long.
Andreas Bulling understands that this software will open up the ground-breaking innovation of other computer-supported personality testing programs, which also triggers the chances of this innovation being wrongly abused if it falls into the hands of illegal companies and autocratic governments that are already busy in rampantly carrying out digital analysis to study modern human behaviour.
However, Andreas Bulling firmly believes that this technology is far from being adequate for the task of interpreting and discovering personality traits and providing reliable information without any assistance from humans. This is mainly because presently, it requires the subject to wear the eye tracker exactly in the front of their eyes.
If this software should be capable of successfully evaluating human personality traits and provide reliable information without any kind of human assistance, then this innovative technology, like all other ground-breaking inventions, can prove to be an extremely beneficial technological milestone for mankind.
Andreas Bulling is reported to have said,
We are scientists, we can only make the technology available and show what’s possible. The way in which the technology is used must be regulated by society and by law.