An Interactive App for Social Skills Training in Autism Spectrum Disorder

Background:  Deficits in social communication are defining features of autism spectrum disorder (ASD). These deficits negatively affect long-term outcomes for those with ASD and have been associated with unemployment and under-employment, low rates of independent living, and increased risk of psychiatric disorders. While prognosis can be significantly improved with intervention, few evidence-based clinical interventions exist for social skill deficits in ASD. Existing interventions are resource-intensive, their outcomes vary widely for different individuals, and they often do not generalize to new contexts. Technology-aided intervention is a motivating, low-cost, and versatile approach for social skills training in ASD. It can provide a safe and controlled venue for rehearsal of skills in a self-paced and personalized manner, allow for treatments to be implemented with high precision and fidelity, and reduce the cost, resource, and other accessibility barriers to existing treatments. Although early studies support the feasibility and potential effectiveness of technology-aided intervention for social skills training in ASD, existing approaches have been criticized for their shortcomings in teaching skills that can be generalized to new contexts. 

Objectives:  The objective of this study is to build and evaluate a novel technology for supporting social skills training in children with ASD in order to facilitate skill generalization.

Methods:  An interactive “app” was developed on the Android platform to allow rehearsal of skills in social situations. Building on key strategies for teaching generalizable skills in ASD, the app features rehearsal with variation (repetition of skills across different situations), systematic fading of prompts (decreasing user supports with progress), reinforcement (rewards for positive behaviours), and feedback (reports of user performance). Each social scenario is designed as a multi-level game that personalizes training based on each child’s needs and strengths. At each level, the scenario details (e.g., background, interaction partner) are varied. With increasing difficulty level, the amount of visual and auditory noise increases and user prompts decrease. To allow seamless user interactions, the app employs speech recognition and generation. An eye-tracking algorithm is used to ensure appropriate eye contact throughout the interaction. Various features for personalization of scenarios and rewards are provided for both the child and the caregiver.

Results:  A fully functional prototype has been implemented (Figure 1). A usability study with 10 children with ASD is in progress.

Conclusions:  To the best of our knowledge, Holli is the first interactive technology-supported prompting system for social skills training in ASD. This app can ultimately improve outcomes for individuals with ASD by providing a portable, accessible, and cost-effective system for social skills intervention.