As the future doors are opening in front of us, the impossible AI techniques are also becoming visibly possible. According to a recent study, AI can now detect our personalities just by watching our eye movements. The study suggests the fact that our eyes can actually reveal the most of our feelings deep inside.

The research:

A neuropsychologist Tobias Loetscher from the University of South Australia has led the research. He and his team recruited 50 people to volunteer. Each of them had to answer the questions about five big personality traits. These include openness, conscientiousness, neuroticism, agreeableness, and extraversion. This indicated the high and low levels of traits in participants.

Also, the volunteers wore eye-tracking headsets for the recording of their eye movements for 10 minutes. Meanwhile, they were made to visit shopping stores. After the whole process of machine learning, the research found out that it is possible to recognize patterns of eye movements and match them with basic psychological personalities.

Consequently, Loetscher said, “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.”

However, their previous research suggested that our eye movements are directly proportional to the way we think or feel. This is a normal human tendency that we pick up during interpersonal relations.

The result:

“One key contribution of our work is to demonstrate, for the first time, that an individual’s level of neuroticism, extraversion, agreeableness, conscientiousness, and perceptual curiosity [another personality type] can be predicted only from eye movements recorded during an everyday task,” the research paper explains.

Although it is important to note that AI was not able to predict the personality types with full accuracy. However, the researchers said that it was reliable up to 15 percent, better than what they expected.

“People are always looking for improved, personalized services. However, today’s robots and computers are not socially aware, so they cannot adapt to non-verbal cues,” Loetscher said. He further added, “This research provides opportunities to develop robots and computers so that they can become more natural, and better at interpreting human social signals.”

Final thought on this AI:

This advancement in AI technology can really help to improve interactions with the machines. Also, it will give virtual assistants (like robots) a way to detect human moods and emotional states. But apart from the positives, there are some negative impacts too. If the optical sensors would literally sense our psychology, then there are some privacy concerns. Scientists have to keep this in mind before further advancements in this field.