WFXB FOX: Computer can tell if you're a match

UC trained a computer to identify types of conversations based on the participants' physiology

WFXB Fox-TV highlighted research by engineers at the University of Cincinnati who taught a computer to recognize types of conversations based on the participants' physiology alone.

Researchers studied a phenomenon in which people’s heart rates, respiration and other autonomic nervous system responses become synchronized when they talk or collaborate. Known as physiological synchrony, this effect is stronger when two people engage deeply in a conversation or cooperate closely on a task.

In experiments with human participants, the computer was able to differentiate four conversation scenarios with as much as 75% accuracy. The study is one of the first of its kind to train artificial intelligence how to recognize aspects of a conversation based on the participants’ physiology alone.

The study was published in the journal IEEE Transactions on Affective Computing.

Lead author and UC doctoral student Iman Chatterjee said a computer could give you honest feedback about your date — or yourself.

“The computer could tell if you’re a bore,” Chatterjee said. “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.”

UC Associate Professor Vesna Novak said this field of affective computing could provide feedback to educators, therapists or other people who want to understand what's really going on in interpersonal dynamics.

Read the Fox-TV story.

Featured image at top: UC engineering students connected to sensors have a conversation while UC Associate Professor Vesna Novak monitors their physiological responses on a computer. Photo/Andrew Higely/UC Marketing + Brand

More UC engineering in the news

UC engineering associate professor Vesna Novak is using machine learning to study physiological synchrony, the phenomenon in which the heartbeats and respiration between two people engaged in conversation or collaboration mirror each other. With students Benjamin Miller and Iman Chatterjee.

A computer screen shows the physiological responses of a person engaged in conversation. Photo/Andrew Higley/UC Marketing + Brand

Related Stories

2

Dayton Inno: UC alumni develop wearable safety device for runners

October 28, 2021

University of Cincinnati biomedical engineering graduate Jack Randall is developing a wearable safety device for runners and cyclists. Zoza, a small, wearable SOS device, can be attached to a shoe or zipper and is intended for endurance athletes who often don’t carry a phone or who travel through remote areas. A user can press a button to send an emergency alert and the device even works in locations where cell service is unavailable.