Developing an AI Model to Identify Math and Literacy Instruction in Early Childhood Education Classrooms 

Abstract

High-quality early childhood classrooms provide children with a nurturing environment to develop their physical, social, and academic capabilities. Accurately identifying when instruction occurs in early childhood classrooms is essential for supporting high-quality teaching and understanding children’s learning experiences. This technical white paper explores the feasibility of using AI and classroom video to automatically detect math and literacy instructional moments in pre-K settings. Building on SRI’s existing models, originally developed to identify academic content in YouTube video, this study applied a multimodal machine learning framework to pre-K classroom video recordings. Included are details on codebook development, human annotation procedures, model performance, and key limitations and implications for using AI-enabled tools to support instructional quality in early learning settings.