Study Suggests Robots Can Be Used to Assess Mental Wellbeing of Children

A new study out of the University of Cambridge suggests that robots can be better at detecting mental wellbeing issues in children when compared to parent-reported or self-reported testing. 

The research was presented at the 31st IEEE International Conference on Robot & Human Interactive Communication (RO-MAN) in Naples, Italy. 

Supplementing Traditional Methods of Mental Health

The team consisted of roboticists, computer scientists, and psychiatrists, and the study involved 28 children between the ages of eight and 13. There was also a child-sized humanoid robot that carried out a series of standard psychological questionnaires that helped assess the mental wellbeing of each participant. 

The study, which was the first of its kind, found that the children would often confide in the robot, and they even shared information that they had not shared via online or in-person questionnaires. 

According to the team, robots could supplement traditional methods of mental health assessment.

Professor Hatice Gunes leads the Affective Intelligence and Robotics Laboratory in Cambridge’s Department of Computer Science and Technology. 

“After I became a mother, I was much more interested in how children express themselves as they grow, and how that might overlap with my work in robotics,” Gunes said. “Children are quite tactile, and they’re drawn to technology. If they’re using a screen-based tool, they’re withdrawn from the physical world. But robots are perfect because they’re in the physical world — they’re more interactive, so the children are more engaged.” 

Experiment and Observations

Gunes and her team, along with colleagues in Cambridge’s Department of Psychiatry, designed an experiment to see if robots could help assess mental wellbeing in children. 

Nida Itrat Abbasi is the study’s first author. 

“There are times when traditional methods aren’t able to catch mental wellbeing lapses in children, as sometimes the changes are incredibly subtle,” Abbasi said. “We wanted to see whether robots might be able to help with this process.” 

Each participant took part in a one-to-one 45-minute session with a Nao robot, which is a humanoid robot about 60 centimeters tall. A parent or guardian, and members of the research team, observed from an adjacent room. 

Before each session, the children and their parents or guardians completed online questionnaires. 

The robot performed four different tasks during each session. First, it asked open-ended questions about happy and sad memories over the last week. It then administered the Short Mood and Feelings Questionnaire (SMFQ). Next, it administered a picture task inspired by the Children’s Apperception Test (CAT), where children are asked to answer questions related to pictures shown. Finally, the robot administered the Revised Children’s Anxiety and Depression Scale (RCADS) for generalized anxiety, panic disorder, and low mood. 

The children were split up into three different groups after the SMFQ, and they were organized based on how likely they were to be struggling with their mental wellbeing. They then interacted with the robot throughout the sessions, speaking to it or touching sensors on its hands and feet. There were also additional sensors that monitored the participants’ heartbeat, head and eye movements. 

The researchers found that the way the children interacted with the robot was related to the varying levels of wellbeing concerns they had. For example, children that might not be experiencing mental wellbeing-related problems were found to have more positive interactions with the robot. For children that might be experiencing these wellbeing-related concerns, the robot could enable them to talk about true feelings and experiences, leading to negative responses. 

“Since the robot we use is child-sized, and completely non-threatening, children might see the robot as a confidante — they feel like they won’t get into trouble if they share secrets with it,” Abbasi said. “Other researchers have found that children are more likely to divulge private information — like that they’re being bullied, for example — to a robot than they would be to an adult.”

The researchers made sure to point out that this is not a substitute for human interaction. 

“We don’t have any intention of replacing psychologists or other mental health professionals with robots, since their expertise far surpasses anything a robot can do,” co-author Dr. Micol Spitale said. “However, our work suggests that robots could be a useful tool in helping children to open up and share things they might not be comfortable sharing at first.” 

The team will now look to expand their survey and include more participants while also following them over longer periods of time.