Min Li

Research

I believe that assessments should go beyond measuring learning outcomes; they should empower students and improve how they learn. My research aims to study and model how student learning can be accurately, adequately, and fairly assessed both in large-scale testing and classroom settings, especially in tech-rich settings, so that rich and actionable assessment results can be offered to learners and educators. All my work reflects the combination of cognitive sciences and psychometric modeling approaches in STEM disciplines in various projects with a closer focus on validity issues and validation considerations, including examining cognitive demands of science items to streamline and reimagine the science of item development, using natural language processing methods to catalog and detect sources of testing bias, modeling methods with student process data to diagnose students’ reasoning and problem-solving strategies, automated grading of students’ written responses to formatively assess their strategy uses and error types in fraction problems, measurement issues in constructing instructionally sensitive tasks, issues of testing linguistic minority students in STEM, etc. 

Latest Research Projects:

• PI, Development and Validation of a Versatile and Equitable Assessment of Knowledge within the Standard First Course in Computer Science, NSF IUSE program (NSF-2417208, 10/1/2024-9/30/2026)

• Co-PI, Harvesting Actionable Results for Learning and Instruction (HARLI): A Novel Mixed Methods Approach to Extracting and Validating Information from Diagnostic Assessment, NSF ECR Core research program (NSF-2300382, 9/1/2023-8/31/2026)

• Co-PI, Collaborative: Developing Authentic and Fair Computer Science Assessments, NSF ECR-HER Core research program (NSF-2100296, 10/1/2021-9/30/2026)

• Co-PI, Automated Classification of Student Problem-Solving Style in Representing Fractions with a Number Line, Jaffe Foundation (2/1/2023-2/28/2026)

Latest Papers:

Zhang, D., Wang, Z., & Li, M. (2025). Visual translator: bridging students’ handwritten solutions and automatic diagnosis of students’ use of number lines to solve fraction problems. Educational Science, 15(12), 1638. DOI: https://doi.org/10.3390/educsci15121638

Gao, Y., Zhai, X., Li, M., Lee, G., & Liu, X. (2025). A multimodal interactive framework for science assessment in the era of generative artificial intelligence. Journal of Research in Science Teaching, 62(9), 2014-2028. DOI: https://doi.org/10.1002/tea.70009