Using Artificial Intelligence to Extract Curriculum Insights from Student Evaluations of Teaching in Higher Education
Location
Seminole B
Start Date
29-5-2025 9:00 AM
End Date
29-5-2025 9:25 AM
Description
This project presents a structured, AI-enhanced framework for extracting actionable curriculum insights from student evaluations of teaching (EOT) within professional veterinary education. Set in a competency-based, integrated Doctor of Veterinary Medicine (DVM) program, the process begins by establishing the programmatic context, ensuring that teaching evaluation data is interpreted appropriately. The framework guides users through five key steps: categorizing qualitative feedback into core curriculum domains (Pace, Integration, Instructional Resources, Communication), selecting representative comments, assigning sentiment-based scores, identifying outliers, and generating structured administrator reports. AI-driven tools, including natural language processing and sentiment analysis, support the systematic classification and quantification of student feedback. This methodology promotes consistent, data-informed decisions for curriculum enhancement and instructional development. The process is replicable, scalable, and designed to support continuous quality improvement in veterinary and other health professions education settings.
Recommended Citation
Schmidt, Marcelo; Urzola, Federico; and Mori, Howard Rodriguez, "Using Artificial Intelligence to Extract Curriculum Insights from Student Evaluations of Teaching in Higher Education" (2025). Teaching and Learning with AI Conference Presentations. 17.
https://stars.library.ucf.edu/teachwithai/2025/thursday/17
Using Artificial Intelligence to Extract Curriculum Insights from Student Evaluations of Teaching in Higher Education
Seminole B
This project presents a structured, AI-enhanced framework for extracting actionable curriculum insights from student evaluations of teaching (EOT) within professional veterinary education. Set in a competency-based, integrated Doctor of Veterinary Medicine (DVM) program, the process begins by establishing the programmatic context, ensuring that teaching evaluation data is interpreted appropriately. The framework guides users through five key steps: categorizing qualitative feedback into core curriculum domains (Pace, Integration, Instructional Resources, Communication), selecting representative comments, assigning sentiment-based scores, identifying outliers, and generating structured administrator reports. AI-driven tools, including natural language processing and sentiment analysis, support the systematic classification and quantification of student feedback. This methodology promotes consistent, data-informed decisions for curriculum enhancement and instructional development. The process is replicable, scalable, and designed to support continuous quality improvement in veterinary and other health professions education settings.