Student Reasoning Patterns in Science (SPIN-Science)
The SPIN-Science project develops an AI-supported classroom assessment tool designed to measure how middle-school students reason when engaging in scientific argumentation about ecosystem phenomena. By embedding artificial intelligence into classroom assessments, the project aims to provide real-time diagnosis of student reasoning patterns and immediate feedback that supports both teachers and learners.
Researchers will use natural language processing and psychometric methods to analyze students’ written responses and identify key components of scientific argumentation, including claims, evidence, and rebuttals. The tool is designed to support diverse learners, especially English learners (ELs), by capturing a wide range of linguistic features and reasoning strategies. Through iterative development, pilot testing, and large-scale field studies, the team will validate the system’s cognitive, instructional, and inferential effectiveness.
The project seeks to advance AI-supported assessment practices in science education while helping educators better understand student thinking and improve instructional decision-making. Ultimately, SPIN-Science aims to create a scalable, validated tool that supports equitable science learning and strengthens classroom assessment practices.
Institute of Education Sciences (IES) — NCER
Funding: $1,999,682
Timeline: 2024–2028
Program: Education Research Grants (Cognition & Student Learning)
Principal Investigator
Lei Lui
Dr. Lei Liu is a research director leading the K–12 research team at the ETS Research Institute and an adjunct professor at the University of Pennsylvania. She holds a PhD in educational psychology from Rutgers University, specializing in learning sciences and educational technology. Her research focuses on science learning, assessment, and AI-supported educational tools, with an emphasis on preparing students for postsecondary education and the workforce. Dr. Liu has led multiple federally funded STEM education projects and has authored over 70 peer-reviewed publications. She also serves on the editorial board of Instructional Science and supports major ETS programs, including California state assessments and NAEP science and mathematics initiatives.
Co-Principal Investigator
Xiaoming Zhai
Xiaoming Zhai, assistant professor at University of Georgia, is the principal investigator of the AI Bias project. He uses AI in science assessment scoring and investigates whether the AI algorithms more biased than humans when scoring Students from UnderRepresented groups in STEM’s (SURSs’) drawing models and writing explanations in scientific modeling practice. Also, he tries to explore whether AI algorithms are more sensitive to the linguistic and cultural features of the assessments than human experts.
