Robots may be better at detecting mental well-being problems in children than tests carried out by the parents or by themselvessuggests a new study presented at the 31st IEEE International Conference on Interactive Communication Between Robots and Humans (RO-MAN), being held in Naples, Italy.
A team of roboticists, computer scientists and psychiatrists at the University of Cambridge in the UK conducted a study with 28 children between the ages of 8 and 13, and had a child-sized humanoid robot administer a series of standard psychological questionnaires to assess the mental well-being of each participant.
The children were willing to trust the robot, and in some cases shared with it information that they had not yet shared through the standard assessment method of online or in-person questionnaires. It is the first time that robots have been used to assess the mental well-being of children.
The researchers say the robots could be a useful complement to traditional methods of mental health assessment, although they are not intended to replace professional mental health support.
During the COVID-19 pandemic, homeschooling, financial pressures, and isolation from peers and friends took a toll on the mental health of many children. However, even before the pandemic, anxiety and depression among UK children have been on the rise, but resources and support to address mental wellness are very limited.
Professor Hatice Gunes, who heads the Robotics and Affective Intelligence Laboratory at Cambridge’s Department of Computer Science and Technology, has studied how social assistance robots (SAR) can be used as mental wellness “coaches” for adultsbut in recent years he has also studied how they can be beneficial for children.
“After becoming a mother, I became much more interested in the way children express themselves as they grow up, and how that might coincide with my work in robotics,” Gunes explains. “Children are quite tactile and are attracted to technology. If they use a screen-based tool, they remove themselves from the physical world. But robots are perfect because they’re in the physical world: they’re more interactive, so kids are more engaged.”
With his colleagues at the Cambridge Department of Psychiatry, Gunes and his team devised a experiment to see if robots could be a useful tool to assess the mental well-being of children.
“There are times when traditional methods are not able to capture mental well-being failures in children, as sometimes the changes are incredibly subtle -says Nida Itrat Abbasi, first author of the study-. We wanted to see if robots could help in this process.”
For the study, 28 participants between the ages of 8 and 13 participated in a 45-minute one-on-one session with a Nao robot, a humanoid robot about 60 centimeters tall. One of the parents or guardians, together with the members of the research team, watched from an adjacent room. Before 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. First, she asked open-ended questions about happy and sad memories from the last week. “Second, she administered the Brief Mood and Feelings Questionnaire (SMFQ).
Thirdly, he administered an imagery task inspired by the Child Apperception Test (CAT), in which children are asked to answer questions related to the displayed images, and finally he administered the Revised Childhood Anxiety and Depression Scale (RCADS). ) to detect generalized anxiety, panic disorder, and low mood.
The children were divided into three different groups after the SMFQ, based on how likely they were to have problems with their mental well-being. Participants interacted with the robot throughout the session by talking to it or by touching the sensors on the robot’s hands and feet. Other sensors tracked participants’ heartbeats and head and eye movements during the session.
All study participants said they they liked to talk to the robot and some shared with him information that they had not shared either in person or in the online questionnaire.
The researchers found that children with different levels of well-being problems interacted differently with the robot. For children who did not have problems related to mental well-being, the researchers found that interaction with the robot led to more positive responses in the questionnaires.
However, for children who might be experiencing wellness-related issues, the robot could have allowed them to divulge their true feelings and experienceswhich led to more negative ratings on the questionnaire.
“Because the robot we used is the size of a child and poses no threat, children may see the robot as a confidant, as they feel they will not get in trouble if they share their secrets with it,” Abbasi explains. Other researchers have discovered that children are more likely to divulge private information -like they are harassing, for example- a robot than an adult”.
The researchers say that while their results show that robots could be a useful tool for the psychological evaluation 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,” says co-author Dr Micol Spitale. “However, our work suggests that robots could be a useful tool to help kids open up and share things they might not be comfortable with at first.” The researchers claim that they hope to expand their study in the future, including more participants and following them over time. They are also investigating whether similar results can be achieved if children interact with the robot via video chat.