class = “sc-cffd1e67-0 fmXrkB”>
The AI recognized the briefest emotions, such as a brief smile or an expression of disgust, within a millisecond interval. As the University of Basel explained on Wednesday, such so-called “micro-expressions” can be missed by therapists.
Overall, AI evaluated facial expressions in psychotherapeutic situations as reliably as humans, as a statistical comparison with three therapists showed in the study published in the journal “Psychopathology.”
Researchers trained a freely available artificial neural network with more than 30,000 facial photos to recognize six basic emotions of happiness, surprise, anger, disgust, sadness and fear. Trained in this way, the AI then analyzed video recordings of 389 therapy sessions from 23 borderline patients.
“We were surprised that relatively simple AI systems were able to interpret facial expressions and emotions so robustly,” lead author Martin Steppan said in the University of Basel announcement.
According to Steppan, artificial intelligence could serve as a tool for psychotherapists in the future. According to the University of Basel, it takes a lot of time to evaluate and interpret facial expressions recorded for research projects or psychotherapy. That’s why experts often resort to less reliable indirect methods, such as measuring skin conductivity, the university wrote. Artificial intelligence could provide a cure and thus become an important tool in therapy and research.
Steppan nevertheless emphasized that interpersonal relationships remain important. Therapeutic work is primarily relationship work and therefore remains a human domain. “At least for now,” the psychologist said. (SDA)
Source : Blick
I am Dawid Malan, a news reporter for 24 Instant News. I specialize in celebrity and entertainment news, writing stories that capture the attention of readers from all walks of life. My work has been featured in some of the world’s leading publications and I am passionate about delivering quality content to my readers.
