Presentation Schedule
AI-Powered Feedback for Constructed Response Science Items: Improving Teacher Efficiency, Instructional Practices, and Student Learning Outcomes (92967)
Session Chair: Hyesun You
This presentation will be live-streamed via Zoom (Online Access)
Saturday, 14 June 2025 10:15
Session: Session 1
Room: Live-Stream Room 3
Presentation Type:Live-Stream Presentation
– click here to convert to your timezone
Providing personalized feedback for constructed response (CR) science items is a critical component of effective teaching, yet it often presents challenges related to time constraints and consistency in scoring. This study explores the role of AI-powered feedback systems in supporting teachers' instructional practices and enhancing the efficiency of evaluating CR science assessments. Constructed responses allow students to demonstrate higher-order thinking and their ability to articulate scientific reasoning; however, they require detailed and individualized feedback, which can be resource-intensive for educators. Leveraging AI for automated or semi-automated feedback presents an opportunity to save time while maintaining the instructional value of formative assessment. This study investigates the implementation of AI-driven feedback systems for CR science items and their impact on teachers' instructional decisions and workflow. Specifically, it examines how AI tools support teachers in delivering timely, consistent, and actionable feedback to students, thereby promoting student learning without compromising assessment rigor. The research employs a mixed-methods approach, combining teacher interviews, classroom observations, and an analysis of student performance data to evaluate the effectiveness of AI feedback systems. Findings suggest that these systems reduce grading time, increase teachers' capacity to focus on instructional planning, and enhance student engagement by providing more relevant feedback tailored to individual learning needs. The study contributes to the growing body of research on the integration of AI in science instruction and underscores the potential for AI-driven feedback systems to transform instructional practices, enabling teachers to efficiently evaluate CR items while fostering deeper scientific understanding in students.
Authors:
Hyesun You, The University of Iowa, United States
About the Presenter(s)
Dr. Hyesun You is currently an Assistant Professor of Science Education at the University of Iowa, United States.
See this presentation on the full schedule – Saturday Schedule
Conference Comments & Feedback
Place a comment using your LinkedIn profileShare this Presentation
Comments
Powered by WP LinkPress