Collaborative research: enhancing stem instructor reflection by automatically detecting instructional practices

The National Science Foundation Division of Undergraduate Education awarded The University of Iowa $305,928 on October 1, 2026, under the STEM Education program (CFDA 47.076) to develop an automated tool that detects instructional practices in STEM higher education classrooms and provides tailored feedback to instructors.

The project creates a free-to-use platform enabling STEM instructors to reflect on their teaching by receiving automated, practice-specific feedback designed to prompt genuine reflection and support instructional improvement. The work encompasses analysis of large-scale classroom observation data, validation of automated instructional practice detection algorithms, development of instructor-facing feedback features, and study of instructor adoption and effectiveness of the tool. The project simultaneously aims to advance understanding of instructional characterization through advanced data mining approaches applied to large-scale observations of classroom behaviors. For educational researchers, the effort documents instructional practices at scale, supporting research on teaching practices and student success.

Performance occurs in Iowa City, Iowa, with a period of performance from October 1, 2026, through September 30, 2029. This is a Level 1 Engaged Student Learning project within the NSF IUSE: EDU program, which supports research and development projects to improve STEM education effectiveness.

Abstract

This project aims to serve the national interest by 1) automatically determining what instructional practices are being used in stem higher education classrooms, and 2) sharing those practices with instructors in the service of educational improvement. This level 1 engaged student learning project addresses a key problem in modern stem education: identifying instructional practices can be a time-consuming and subjective process. This project is designed to provide a carefully redesigned, free-to-use tool that allows stem instructors to reflect on their current instructional practices by receiving tailored advice. For educational researchers, the project has the potential to document instructional practices at scale thereby supporting research on teaching practices and student success. The primary goal of this project is to create a tool that allows stem instructors to receive automated feedback about their instruction that prompts genuine reflection and supports improvement of instruction. The scope includes the analysis of large-scale classroom observation data, validation of automated instructional practice detection, development of instructor-facing feedback features, and study of instructor use of the tool. In the development of this tool, this project aims to simultaneously advance the understanding of instructional characterization via advanced data mining approaches of large-scale observations of classroom behaviors. After instructional patterns are validated, the project plans to develop a tool that seeks to improve instructional quality, which in turn improves student learning outcomes. This project also includes plans to study the effectiveness of the developed tool as well as how to improve IT. The NSF iuse: EDU program supports research and development projects to improve the effectiveness of stem education for all students. Through the engaged student learning track, the program supports the creation, exploration, and implementation of promising practices and tools. 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.- subawards are not planned for this award.