AI recognizes the shortest emotions better than therapists
Published: Wednesday, Dec 27th 2023, 13:20
Retour au fil d'actualité
Artificial intelligence (AI) can recognize emotions based on facial expressions. In a feasibility study by researchers at the University of Basel, AI performed even better than trained therapists in some areas.
The AI was able to recognize the shortest emotional expressions in the millisecond range, such as a brief smile or an expression of disgust. Such so-called "micro expressions" can escape therapists, as the University of Basel announced on Wednesday.
Overall, the AI judged facial expressions in psychotherapeutic situations as reliably as humans, as the statistical comparison with three therapists in the study published in the journal "Psychopathology" showed.
Trained with 30,000 photos
The researchers trained a freely available artificial neural network with over 30,000 facial photos to recognize the six basic emotions of happiness, surprise, anger, disgust, sadness and fear. This trained AI then analyzed video recordings of 389 therapy sessions of 23 borderline patients.
"We were surprised that relatively simple AI systems can interpret facial expressions so robustly in terms of their emotions," said first author Martin Steppan in the press release from the University of Basel.
People remain important
According to Steppan, AI could serve as a tool for psychotherapists in the future. According to the University of Basel, the evaluation and interpretation of recorded facial expressions for research projects or psychotherapy is very time-consuming. Experts therefore often resort to less reliable indirect methods such as measuring skin conductivity, the university wrote. AI could provide a remedy and thus become an important tool in therapy and research.
Nevertheless, interpersonal relationships remain important, Steppan emphasized. Therapeutic work is first and foremost relationship work and thus remains a human domain. "At least for the time being," says the psychologist.
©Keystone/SDA
French 
English 
German 
Spanish 
Arabic