Artificial Intelligence in Science and Mathematics Assessment for Students with Disabilities: Opportunities and Challenges

Abstract

Emerging developments in artificial intelligence present significant opportunities to enhance equity and access to science and mathematics assessment content for students with disabilities. Artificial intelligence (AI) technologies may have the potential to support test developers in creating more inclusive assessments that better measure what students know and can do. But they must also consider the potential accessibility challenges or introduction of construct-irrelevant variance posed by these technologies. The purpose of this article is to provide a conceptual overview of the issues to be considered when creating and implementing large-scale science and mathematics assessments for students with disabilities. We discuss how AI has been utilized in large-scale assessments to date and describe the opportunities and potential pitfalls in the stages of the process: assessment design, development, administration, scoring, reporting, and data use. This article concludes with proposed priorities for research that will advance the responsible practice of AI in large-scale assessment that is inclusive, fair, and valid for students with disabilities. This article contributes to the growing body of information on AI applications for assessment by identifying the roles that AI can play in science and mathematics assessment practices and demonstrating how AI can inform approaches to equitable science, technology, engineering, and mathematics (STEM) learning.