After a first date it’s normal to wonder if those warm, fuzzy feelings are reciprocated.
Now, experts are one step closer to an app that will tell you if they’re ‘just not that into you’.
Researchers have trained a computer – using data from wearable technology that measures respiration, heart rates and perspiration – to identify the type of conversation two people are having.
In experiments with 16 pairs of participants, it was able to differentiate four different conversation scenarios with as much as 75 per cent accuracy.
Lead author Iman Chatterjee, from the University of Cincinnati, said the technology could one day give you honest feedback about yourself or your date.
‘The computer could tell if you’re a bore,’ he 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.’
The researchers used the phenomenon of physiological synchrony as part of their design.
This is when people’s heart rates, respiration and other bodily responses become synchronised when they talk or collaborate – an effect that is stronger when two people engage deeply in a conversation or cooperate closely on a task.
Experts are a step closer to developing an app that will tell you how keen a date is on you (file photo)
Experts from the University of Cincinnati (filed) said the technology could one day give you honest feedback about yourself or your date
A computer has been trained to use data from wearable technology that measures respiration, heart rates and perspiration to identify the type of conversation two people are having
Mr Chatterjee said physiological synchrony is most likely an evolutionary adaptation that takes place subconsciously.
‘It is certainly no coincidence,’ he said. ‘We only notice physiological synchrony when we measure it, but it probably creates a better level of coordination.’
The participants involved in the study were asked to take part in four types of conversations.
These included a positive conversation in which they happily talked about a topic in which they shared a similar opinion, a negative conversation in which they unhappily discussed a topic over which they disagree, and two conversations about an agreeable topic.
During this the computer measured their chest and nose respiration, heart rate, skin conductance – for example sweat – and peripheral skin temperature.
In a trial, the AI was able to identify if a conversation was one-sided, two-sided, positive or negative based solely on what it was told by the participants’ bodies, on three out of four occasions (file image)
The findings raise questions about other information computers can tell us about interpersonal relations, researchers say (file image)
Three out of four times, the artificial intelligence was able to identify whether the conversation was one-sided, two-sided, positive or negative based solely on what the participants’ bodies told the machine.
Study co-author Vesna Novak, an associate professor of electrical engineering, said their findings raise questions about what else computers can tell us about interpersonal relations.
‘Our next step is to see how much nuance we can separate,’ she said. ‘We’ve shown that AI has the ability to identify positive versus negative conversations, but can you separate shades of grey that humans wouldn’t discern?’
The findings, published in the journal IEEE Transactions on Affective Computing, read: ‘In the future, such classification algorithms may be used to provide real-time feedback about conversation mood to participants.’