AI has learned to predict presence of sympathy on first date

American scientists from the University of Cincinnati have developed an algorithm based on artificial intelligence (AI) that determines a person's emotions during a conversation with a partner by analyzing indicators such as heart rate, breathing, and perspiration. The research was published in the scientific journal IEEE Transactions on Affective Computing (IEEE TAC).

In their work, the authors aimed to better understand the phenomenon of physiological synchrony, where the breathing and pulse of individuals synchronize during communication or collaborative activities, indicating sympathy towards each other.

In the experiment, 36 individuals were involved, divided into 18 pairs. During tests, participants interacted with each other according to different conversation scenarios designed to evoke various emotional reactions. While conversing, scientists recorded the biological indicators of the volunteers.

Based on the collected data, the researchers developed an algorithm for classifying types of conversations based on physiological indicators. The neural network was able to determine people's emotions in various scenarios with an accuracy of 75%.

The findings of the study can be applied in practice to evaluate the outcomes of a wide range of communications, including the dynamics of dates or any other conversations.