2023-12-29 18:45:42
It is said that the face is the mirror of the soul. It is an expression in a figurative sense, but what is true is that the face usually functions as a mirror of the person’s emotional state.
Interpreting facial expressions as part of psychotherapy or psychotherapeutic research, for example, is a very effective way to determine how a person is feeling at that particular moment. Back in the 1970s, psychologist Paul Ekman developed a standardized coding system to assign basic emotions such as happiness, disgust or sadness to a facial expression in an image or video sequence.
Ekman’s system is widespread and represents a standard in psychological research on emotions.
But the process of analyzing and interpreting recorded facial expressions in research or psychotherapy projects is time-consuming, so psychiatrists often use faster but less reliable indirect methods, such as skin conductance measurements. , which can also be a measure of emotional arousal.
Martin Steppan’s team at the University of Basel in Switzerland set out to find out whether artificial intelligence systems can reliably determine patients’ emotional states from video recordings.
The researchers used freely available artificial neural networks that were trained to detect six basic emotions (happiness, surprise, anger, disgust, sadness and fear) using more than 30,000 facial photos. Next, this artificial intelligence system analyzed video data from therapy sessions with a total of 23 patients with borderline personality pathology. The artificial intelligence system, operating on a high-performance computer, had to process more than 950 hours of video recordings for this study.
The results were surprising: statistical comparisons between the analysis of three trained human therapists and the artificial intelligence system showed a remarkable level of agreement. The artificial intelligence system evaluated facial expressions with the same reliability as a human expert, but was also able to detect even the most fleeting emotions, in the range of milliseconds, such as a brief smile or a fleeting expression of disgust.
A well-trained artificial intelligence system is capable of relating facial microexpressions to the emotions that cause them. (Illustration: Amazings/NCYT)
These types of microexpressions can go unnoticed by therapists or be perceived only subconsciously. Artificial intelligence is, therefore, capable of measuring fleeting emotions with a level of sensitivity higher than that of trained human therapists.
The study is titled “Machine Learning Facial Emotion Classifiers in Psychotherapy Research: A Proof-of-Concept Study.” And it has been published in the academic journal Psychopathology. (Source: NCYT from Amazings)
#Artificial #intelligence #recognize #subtle #signs #emotions #human #faces