American scientists from the University of Cincinnati have developed an algorithm based on artificial intelligence (AI) that determines a person’s emotions when talking to the interlocutor by analyzing indicators such as heart rate, breathing and sweating. The study was published in the scientific journal magazine IEEE Transactions on Affective Computing (IEEE TAC).
In their study, the authors wanted to better understand the phenomenon of physiological synchronization, in which people synchronize their breathing rate and heart rate during communication or joint activities. It is believed that this phenomenon indicates sympathy for another person.
The experiment involved 36 individuals divided into 18 pairs. During the tests, participants interacted with each other in different conversational scenarios designed to evoke different emotional responses. During the conversations, scientists recorded the volunteers’ biological indicators.
Based on the collected data, scientists created an algorithm to classify the type of speech according to physiological indicators. The neural network was able to detect people’s emotions with 75% accuracy in various scenarios.
The results of the research can be applied in practice to evaluate the consequences of a wide range of communication, including the dynamics of a date or any other conversation.
happened before known about creating a hacker method to steal fingerprints using screen tapping sounds.