When OpenAI’s ChatGPT entered the conversation around artificial intelligence (AI) in November 2022, it made the technology mainstream. What was often limited to tech enthusiasts and experts is now being discussed as casually as the price of an egg at the recent Grammys. Following a recent report by McAfee that revealed people are using ChatGPT to write love letters, a new research shows that AI could help daters say, ‘Thank you, next,’ without wasting time.
Engineers at the University of Cincinnati revealed that the technology to tell if a first date is not interested in you might not be far off. In a first-of-its-kind study, published in the journal IEEE Transactions on Affective Computing, researchers trained a computer—using data from wearable technology that measures respiration, heart rates and perspiration—to identify the type of conversation between two people based on their physical responses alone, according to Science Daily.
They studied a phenomenon known as physiological synchrony wherein heart rates, respiration and other autonomic nervous system responses synchronized during conversations. It is stronger when people have deep conversations or closely collaborate on a task. This synchrony also shows up during Zoom calls.
The computer could differentiate between four different conversation scenarios involving human participants with 75% accuracy. "The computer could tell if you're a bore," said Iman Chatterjee, lead author and UC doctoral student. "A modified version of our system could measure the level of interest a person is taking in the conversation, how compatible the two of you are and how engaged the other person is in the conversation."
This technology can also be used to examine how much empathy a patient perceives in a therapist or the engagement levels that students feel with their teachers.
This aspect of affective computing holds huge potential for providing real-time feedback for educators, therapists, or even autistic people, added Vesna Novak, co-author of the study and an associate professor of electrical engineering in UC's College of Engineering and Applied Science.