If you’re not sure whether to smash or pass on your date, there may soon be an app to help you with that.
A study published in IEEE Transactions on Affective Computing journal revealed that artificial intelligence is now able to inform you how well a date went by measuring a person’s sweat, breathing patterns and heart rate.
The study is the first of its kind to “tell if you’re a bore” based solely on vital signs.
Engineers at the University of Cincinnati trained a computer using data from wearable technology to be able to identity the kind of conversation two people are having based on their physiological responses.
Sixteen pairs of participants discussed topics that they could either strongly agree or disagree on before having four different conversations: a positive conversation where they happily discussed a topic they agreed on, a negative conversation where they unhappily discussed something they disagreed on and two conversations about an agreeable topic where each person took turns leading the discussion.
AI was able to determine between four different conversation scenarios with a 75% accuracy rate — even when the conversation was occurring virtually over Zoom.
The results rely on the phenomenon known as “physiological synchrony,” which can show how engaged people are by how their heart rate, respiration rate and perspiration rates all align — and lead researcher Iman Chatterjee said the phenomenon is likely a part of evolutionary adaptation.
He explained that humans evolve to share and collaborate, which can manifest in the subconscious.
Synchrony also correlates with how much empathy a patient gets from a therapist or engagement students feel with teachers.
“It is certainly no coincidence. We only notice physiological synchrony when we measure it, but it probably creates a better level of coordination,” Chatterjee said.
Studies have previously shown that physiological synchrony can tell how well two people will work together to accomplish a task and can probably even be used to see which people in a company or organization work best in a group setting.
“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,” he explained.
“Our next step is to see how much nuance we can separate,” said study co-author Vesna Novak, an associate professor of electrical engineering in UC’s College of Engineering and Applied Science.
“We’ve shown that AI has the ability to identify positive versus negative conversations, but can you separate shades of gray that humans wouldn’t discern?”