SBIR Phase I: A Machine-Learning Tool for Social-Emotional Learning, Development, and Intervention for Remote or Hybrid Child Development Support (COVID-19)

Heykiddo, Llc, Philadelphia PA

Investigators

Abstract

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project is to detect social-emotional issues in children (ages 5-12) for early intervention. A growing trend in juvenile mental health concerns was exacerbated by the recent COVID-19 pandemic and the associated disruption in child development. This project proposes a machine learning (ML) system that learns from interactions with the child and parent independently and can detect potential social-emotional concerns. The ML system enables personalized evaluation and monitoring outside a clinical setting in a remote or hybrid context. This Small Business Innovation Research (SBIR) Phase I project advances algorithms for integration into a social-emotional skill building curriculum. The project proposes: 1) User segmentation based on a comprehensive assessment of social-emotional functioning, 2) Correlation of the relevancy and effectiveness of modules to segmented users, and 3) Collection of information to identify social emotional deficits (red flags). These activities enable a feedback loop to learn and deliver recommendations for each child-parent dyad, personalizing learning in real-time. These algorithms learn from behavioral, social, and emotional inputs from both the parent and child when they engage with the technology. The system will also detect red flags correlated with social and emotional deficits, promoting early intervention. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.