Teaching Emotional Skills to Children with Autism

TDLC's Jim Tanaka at the University of Victoria is partnering with Marni Bartlett at the University of Victoria to create an exciting, innovative software game to help children with autism spectrum with their facial emotions using a state-of-the-art computer technology, Emotient Analytics. Emotion Analytics is a revolutionary web-based platform that evaluates facial expressions in real time via webcam input. Using this state-of-the-technology program, we designed the FaceMaze, a fun interactive game where the player navigates a pacman-like icon through a maze collecting candy points. Blocking the player's path are gremlins that can only be removed by producing the proper facial expression (happy, sad, angry, surprise). The player's expression is recorded and evaluated in real time by the Emotient Analytics software. In a to-be-published study, we found that playing the FaceMaze game for fifteen minutes was sufficient to significantly improve the abilities of children with autism to produce happy and angry expressions as judged by naïve observers.

FaceMaze is an innovative intervention game that addresses impaired social communication, a core symptom of autism. Individuals with autism show profound deficits in their ability to produce and interpret facial emotions. Children with autism have a tendency to produce facial expressions that are either affectively flat or difficult to interpret. Because faces are a primary source of human interaction, the inability to produce facial emotions has adverse consequences for developing good social communication skills. The goal of FaceMaze is to create an intervention treatment that is both fun and effective. The potential impact and benefits of the FaceMaze program are significant. By providing a science- and evidence-based intervention that is engaging, accessible and cost-free, we hope to improve the everyday social lives of children with autism and their families

Children with autism spectrum disorder (ASD) show deficits in their ability to produce facial expressions. In this study, a group of children with ASD and IQ-matched, typically developing (TD) children were trained to produce ''happy'' and ''angry'' expressions with the FaceMaze computer game. FaceMaze uses an automated computer recognition system that analyzes the child's facial expression in real time. Before and after playing the Angry and Happy versions of FaceMaze, children posed ''happy'' and ''angry'' expressions. Naive raters judged the post-FaceMaze ''happy'' and ''angry'' expressions of the ASD group as higher in quality than their pre-FaceMaze productions. Moreover, the post-game expressions of the ASD group were rated as equal in quality as the expressions of the TD group. FaceMaze is a promising, cost-effective training program in facial expression production that is engaging for the child and that can be conducted in a safe, familiar setting.

Gordon, I., Pierce, M. S. & Tanaka, J.W. (in press). Training voluntary facial expressions using automated, real-time feedback. Journal of Autism and Developmental Disorder.