EAGER: AI-powered, Targeted Instructional Support for Early Childhood Teachers

Supporting the development of language, literacy, and STEM skills is essential for children’s future academic success. This project leverages the power of emerging AI technologies to develop a novel, low-cost solution for providing evidence-based instructional support to early education teachers. Specifically, the research team is collaborating with early childhood educators to co-design an AI-powered, app-based platform that delivers targeted instructional feedback to teachers and content-based professional development designed to support children’s development of language, literacy, and STEM skills.

The context for the feedback and novel professional development platform is shared book reading in early education classrooms.

Shared book reading is a common educational activity in pre-school and elementary school classrooms, and quality of teacher talk during shared book reading is predictive of children’s attainment of critical early learning skills. Current approaches to evaluating and providing feedback to teachers about their shared book reading practices necessitate observational measures and human coding, posing practical challenges to providing timely feedback to teachers at scale.

This project represents a transformative approach to the provision of timely feedback to teachers making use of emerging AI technologies. Specifically, the research team first aims to bypass resource-intensive human coding by developing a Natural Language Processing (NLP) pipeline in combination with machine learning (ML) models to harness the power of a large pre-trained model – capable of understanding complex language patterns and contexts – and adapt it to the specific requirements of the educational domain.

Next, the project aims to implement user-centered design in collaboration with early childhood educators to develop an AI-powered app-based platform to deliver timely instructional support, conduct usability testing, and iteratively improve the platform based on educator feedback. Creation of this novel instructional support system advances the knowledge base of how innovative technology solutions can deliver individualized, timely pedagogical support towards improving early learning outcomes.

This project is funded by the Research on Innovative Technologies for Enhanced Learning (RITEL) program that supports early-stage exploratory research in emerging technologies for teaching and learning.

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.