Robots can assess children’s mental well-being, study finds
Robots can better detect mental wellbeing issues in children than parent-reported or self-reported tests, according to a new study.
A team of roboticists, computer scientists and psychiatrists from the University of Cambridge conducted a study of 28 children aged 8 to 13 and asked a child-sized humanoid robot to administer a series standard psychological questionnaires to assess the mental well-being of each participant.
Children were willing to confide in the robot, in some cases sharing information with the robot that they had not previously shared through the standard evaluation method of online or in-person questionnaires. This is the first time that robots have been used to assess children’s mental well-being.
The researchers say the robots could be a useful addition to traditional mental health assessment methods, although they are not intended to replace professional mental health support. The results will be presented today (September 1) at the 31st IEEE International Conference on Robotic and Human Interactive Communication (RO-MAN) in Naples, Italy.
During the COVID-19 pandemic, homeschooling, financial pressures, and isolation from peers and friends have impacted the mental health of many children. However, even before the pandemic, anxiety and depression in children in the UK was on the rise, but resources and support to ensure mental wellbeing are very limited.
Professor Hatice Gunes, who heads the Affective Intelligence and Robotics Lab in Cambridge’s Department of Computing and Technology, has studied how social service robots (SARs) can be used as wellbeing ‘coaches’ mental for adults, but in recent years have also studied how they can be beneficial for children.
“After becoming a mother, I was much more interested in how children express themselves as they grow up and how that might overlap with my work in robotics,” Gunes said. “Children are quite tactile and they are attracted to technology. If they use a screen-based tool, they are removed from the physical world. But robots are great because they’re in the physical world – they’re more interactive, so kids are more engaged.
With colleagues from Cambridge’s Department of Psychiatry, Gunes and his team designed an experiment to see if robots could be a useful tool for assessing children’s mental well-being.
“There are times when traditional methods are not able to detect mental well-being issues in children because the changes are sometimes incredibly subtle,” said Nida Itrat Abbasi, the study’s first author. . “We wanted to see if robots might be able to help with this process.”
For the study, 28 participants between the ages of eight and 13 each took part in a 45-minute one-on-one session with a Nao robot – a humanoid robot about 60 centimeters tall. A parent or guardian, along with members of the search team, observed from an adjacent room. Prior to each session, children and their parents or guardians completed a standard online questionnaire to assess each child’s mental well-being.
During each session, the robot performed four different tasks: 1) asked open-ended questions about happy and sad memories from the past week; 2) administered the Short Mood and Feelings Questionnaire (SMFQ); 3) administered a picture task inspired by the Children’s Apperception Test (CAT), where children are asked to answer questions related to the pictures presented; and 4) administered the Revised Childhood Anxiety and Depression Scale (RCADS) for generalized anxiety, panic disorder, and low mood.
The children were divided into three different groups following the SMFQ, based on how likely they were to experience difficulties with their mental well-being. Participants interacted with the robot throughout the session by talking to it or touching sensors on the robot’s hands and feet. Additional sensors tracked participants’ heart rate, head and eye movements during the session.
The study participants all said they enjoyed talking with the robot: some shared information with the robot that they had not shared either in person or on the online questionnaire.
The researchers found that children with different levels of well-being concerns interacted with the robot differently. For children who might not be experiencing issues related to mental wellbeing, the researchers found that interacting with the robot resulted in more positive response rates to questionnaires. However, for children who might have well-being issues, the robot may have allowed them to divulge their true feelings and experiences, resulting in more negative response rates to the questionnaire.
“Because the robot we use is child-sized and totally non-threatening, kids can see the robot as a confidant – they feel like they won’t get in trouble if they share secrets with him,” Abbasi said. “Other researchers have found that children are more likely to divulge private information – like that they are being bullied, for example – to a robot than to an adult.”
The researchers say that while their results show robots could be a useful tool for the psychological assessment of children, they are not a substitute for human interaction.
“We have no intention of replacing psychologists or other mental health professionals with robots, as their expertise far exceeds anything a robot can do,” said co-author Dr. Micol Spitale. “However, our work suggests that robots could be a useful tool to help children open up and share things they might not be comfortable sharing at first.”
The researchers say they hope to expand their survey in the future, including more participants and following them over time. They are also investigating whether similar results could be achieved if children interact with the robot via video chat.
The research was funded in part by the Engineering and Physical Sciences Research Council (EPSRC), part of UK Research and Innovation (UKRI) and the NIHR Cambridge Biomedical Research Centre.