Our team’s research develops AI/ML methods and studies AI adoptions by integrating educational domain knowledge in curriculum and instruction, learning science, and educational policy and school systems.
Planning and selecting instructional materials is one of the most complex and important components of mathematics teaching. As online instructional materials continue to proliferate, schools and educators are relying on them in addition to textbooks. While there are advantages to open educational resources that are freely available, questions about ensuring their quality and utility to teachers and students remain paramount. An important contribution of this study is identifying ways to measure the quality of large quantities of lesson plans using an integration of cutting-edge machine learning techniques, knowledge of effective mathematics education, and human feedback. Later phases of the project include interviewing teachers about their planning practices, measuring lesson plan quality, and analyzing students’ work to provide multiple perspectives on mathematics lesson plan quality in the middle grades. The use of machine learning to measure lesson plan quality holds transformative potential for the field of mathematics education.
The project will identify ways to analyze large numbers of mathematics lesson plans using a mixed methods approach of natural language processing and human coding. The project focuses on middle grades mathematics lesson and includes data from teachers and students as well as the lesson plan documents themselves. The study has three research aims. First, to develop a shared conceptual framework and specify dimensions of quality lesson plans for middle-grades mathematics by organizing an expert plan of leading researchers and skilled teachers. Second, to develop and validate measures to capture the key dimensions by applying state-of-the-art computer-assisted approaches (e.g., machine learning) and human coding to analyzing a large volume of digital lesson plans obtained under Creative Commons Licenses. Third, to conduct an exploratory sequential mixed-methods study of how teachers attend to, interpret, and select information to create their own lesson plans, and how lesson plan quality is related to students’ completed mathematical work. The mixed methods approach to examining lesson plan quality is an important innovation for advancing research about mathematics teaching and learning.
This project is supported by NSF’s EDU Core Research (ECR) Program. The ECR program emphasizes fundamental STEM education research that generates foundational knowledge in the field. Investments are made in critical areas that are essential, broad and enduring: STEM learning and STEM learning environments, broadening participation in STEM, and STEM workforce development.
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.