As poets have written that the eyes are the mirror of the soul. And now there’s scientific evidence to support the truth of this ancient saying. A team of researchers, led by Tobias Loetscher from the University of South Australia, used machine learning to understand how eye movements and personality are related.
In simple words, the AI determine your personality simply by analyzing your eye moments.
The team of researchers has published a research indicating a link between personality traits and eye movement patterns. The study has been published in a scientific journal called Frontiers in Neuroscience.
The researchers have used state-of-the-art machine learning algorithms to demonstrate their findings. The algorithm was able to find meaningful correlations between eye movement patterns and some major parameters of personality that have been identified by psychologists, like neuroticism, extraversion, agreeableness, and conscientiousness.
The researchers used a mobile, head-mounted device to track the eye movements of forty-two students while they performed a series of activities on campus. Then they gave them a standard questionnaire that assessed the traits of their personalities.
This questionnaire broke down personality into the ‘Big Five’ traits used widely in psychology; extraversion, neuroticism, conscientiousness, agreeableness, and openness to experience.
On feeding the data into the AI algorithm, the researchers found that computers running the algorithm were able to record human eye movements and immediately determine a person’s major personality traits.
The result of the study undertaken by the neuroscience researchers from the University of Stuttgart in Germany and Flinders University in Australia have shown a mind-blowing result.
The prediction accuracy and reliability scores obtained from 42 participants are very promising. The algorithm was able to tracks eye movements to recognize personality type correctly.
In computer vision, state-of-the-art machine learning methods are commonly trained on millions of samples. In this research, the state-of-the-art machine learning methods were fed over a larger dataset with a more representative sample of the general population than the convenience sample.
The large-scale real-world gaze datasets found very helpful to improve automatic inference of personality and to stimulate research on the automatic representation of gaze characteristics.
Tobias Loetscher, the lead researcher of the project, explains:
“Today’s robots and computers are not socially-aware, so they cannot adapt to non-verbal cues.
This research provides opportunities to develop robots and computers so that they can become more natural and better at interpreting human social signals.
Thanks to our machine-learning approach, we not only validate the role of personality in explaining eye movement in everyday life but also reveal new eye movement characteristics as predictors of personality traits.”
AI determine your personality based on various factors and the result generated on this parameter will be your personality. This research revealed many mysterious patterns, that the scientists might not have been able to find without the help of the program. The algorithm has proven as an important breakthrough in social neuroscience,
It may tell us something about the cues that people use unconsciously to assess other people’s personalities in everyday interactions. This knowledge of human non-verbal behavior can also be transferred to socially interactive robots, designed to exhibit human-like behavior.
These systems might in future interact with humans in a more natural and socially acceptable way, thereby becoming more efficient and flexible. It can also be put in smartphones that understand and predict our behavior, potentially offering personalized support.
Advertisers are another sector of society that would love to get their hands on such technology in order to further target campaigns. Researchers warn that this AI determine your personality so it should be regulated so that it cannot be misused by marketers
This research work was funded, in part, by the Australian Research Council, the Cluster of Excellence on Multimodal Computing and Interaction (MMCI) at Saarland University, Germany, as well as a Ph.D. scholarship by the German National Academic Foundation.
More in AI :