MSGID: 1:317/3 63eb0e71   
   PID: hpt/lnx 1.9.0-cur 2019-01-08   
   TID: hpt/lnx 1.9.0-cur 2019-01-08   
    Smash or pass? This computer can tell    
    AI offers insight into conversations using physiology alone    
      
     Date:   
         February 13, 2023   
     Source:   
         University of Cincinnati   
     Summary:   
         Could an app tell if a first date is just not that into   
         you? Engineers say the technology might not be far off. They trained   
         a computer to identify the type of conversation two people were   
         having based on their physiological responses alone.   
      
      
         Facebook Twitter Pinterest LinkedIN Email   
   FULL STORY   
   ==========================================================================   
   Could an app tell if a first date is just not that into you?   
      
   ==========================================================================   
   Engineers at the University of Cincinnati say the technology might   
   not be far off. They trained a computer -- using data from wearable   
   technology that measures respiration, heart rates and perspiration --   
   to identify the type of conversation two people were having based on   
   their physiological responses 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.   
      
   "Physiological synchrony shows up even when people are talking over Zoom,"   
   said study co-author Vesna Novak, an associate professor of electrical   
   engineering in UC's College of Engineering and Applied Science.   
      
   In experiments with human participants, the computer was able to   
   differentiate four different 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."  Chatterjee said   
   physiological synchrony is likely an evolutionary adaptation.   
      
   Humans evolved to share and collaborate with each other, which manifests   
   even at a subconscious level, he said.   
      
   "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."  Studies have shown that physiological synchrony can   
   predict how well two people will work together to accomplish a task. The   
   degree of synchrony also correlates with how much empathy a patient   
   perceives in a therapist or the level of engagement students feel with   
   their teachers.   
      
   "You could probably use our system to determine which people in an   
   organization work better together in a group and which are naturally   
   antagonistic," Chatterjee said.   
      
   This aspect of affective computing holds huge potential for providing   
   real-time feedback for educators, therapists or even autistic people,   
   Novak said.   
      
   "There are a lot of potential applications in this space. We've seen it   
   pitched to look for implicit bias. You might not even be aware of these   
   biases," Novak said.   
      
       * RELATED_TOPICS   
             o Mind_&_Brain   
                   # Perception # Behavior # Consumer_Behavior # Neuroscience   
             o Computers_&_Math   
                   # Computer_Science # Information_Technology #   
                   Artificial_Intelligence # Computers_and_Internet   
       * RELATED_TERMS   
             o Computer_simulation o Computer_vision o   
             Computer-generated_imagery o Nocebo_-_Placebo o   
             Local_area_network o Technology o Computing_power_everywhere   
             o Computer_security   
      
   ==========================================================================   
   Story Source: Materials provided by University_of_Cincinnati. Original   
   written by Michael Miller. Note: Content may be edited for style and   
   length.   
      
      
   ==========================================================================   
   Journal Reference:   
      1. Iman Chatterjee, Maja Gorsic, Mohammad S. Hossain, Joshua D. Clapp,   
      Vesna   
         D. Novak. Automated Classification of Dyadic Conversation Scenarios   
         using Autonomic Nervous System Responses. IEEE Transactions on   
         Affective Computing, 2023; 1 DOI: 10.1109/TAFFC.2023.3236265   
   ==========================================================================   
      
   Link to news story:   
   https://www.sciencedaily.com/releases/2023/02/230213201048.htm   
      
   --- up 50 weeks, 10 hours, 50 minutes   
    * Origin: -=> Castle Rock BBS <=- Now Husky HPT Powered! (1:317/3)   
   SEEN-BY: 15/0 106/201 114/705 123/120 153/7715 226/30 227/114 229/110   
   SEEN-BY: 229/111 112 113 114 307 317 400 426 428 470 664 700 292/854   
   SEEN-BY: 298/25 305/3 317/3 320/219 396/45   
   PATH: 317/3 229/426