Researchers at the Department of Artificial Intelligence in Madrid have developed a way to monitor how primary school children are using computers and determine their engagement levels. This information is then used to decide which action a robot tutor should perform to encourage the child.
Luis Imbernòn Cuadrado, who led the research, said: "The main goal of our work was to design a system that can detect the emotional state of primary school children interacting with educational software and make pedagogic interventions with a robot tutor that can ultimately improve the learning experience.”
The team’s method used the children’s keystrokes and mouse actions to classify the pupils as either concentrating, distracted or inactive. An algorithm was then used to determine a course of action for the robot tutor. This might include encouraging gestures or words, or attempts to engage the child with specific learning objectives.
The research showed that although the technology is not yet ready to replace human teachers, the algorithm and robots could be used to support traditional teaching.
"We consider that robot tutors could have an effective support role to play in the primary school classroom in helping children reach their specific learning objectives," concluded Dr Imbernón Cuadrado.