Kevin is the director of the Automated Analysis of Constructed Responses (AACR) research group. The team explores the use of machine learning and computerized text analysis in science education, applying these techniques to evaluate students’ short written answers as part of assessments in secondary education and undergraduate STEM courses. They have developed computer models that predict expert ratings of student responses with accuracy comparable to inter-rater reliability among expert raters. These techniques can potentially transform assessment practices across STEM disciplines, irrespective of class size.
The research conducted using these technologies aims to provide insights into how students engage in scientific practices and conceptualize “big ideas” in STEM, such as evolution, energy, and genetics.
Kevin earned a Ph.D. in Biochemistry and Molecular Biology from Michigan State University in 2007 and a B.S. in Chemistry from Wayne State University in 2001.
