Alternative Title

Leveraging Artificial Intelligence (AI) for Grading and Feedback: Evaluating ChatGPT's Role in Academic Assessm

Contributor

University of Central Florida. Faculty Center for Teaching and Learning; University of Central Florida. Division of Digital Learning; Teaching and Learning with AI Conference (2025 : Orlando, Fla.)

Location

Universal Center

Start Date

29-5-2025 4:00 PM

End Date

29-5-2025 5:00 PM

Publisher

University of Central Florida Libraries

Keywords:

ChatGPT; Academic assessment; Grading efficiency; Feedback mechanisms; Physics education

Subjects

Grading and marking (Students)--Computer-assisted instruction; Artificial intelligence--Educational applications; Grading and marking (Students)--Evaluation; Academic writing--Evaluation; Physics--Study and teaching--Evaluation

Description

This study evaluates ChatGPT's ability to grade and provide feedback on student responses to an open-ended, constructed, and computational college-level physics exam question by comparing its performance to that of human content experts. Thirty student responses are graded by four experts using an evolving rubric, which is later applied by ChatGPT for scoring and feedback. Preliminary analysis of 10 responses demonstrates strong alignment between ChatGPT and human graders across total scores, performance group distinctions, and rubric criteria. These findings highlight ChatGPT's potential as a valuable tool for improving the efficiency and consistency of educational assessments.

Language

eng

Type

Presentation

Format

application/pdf

Rights Statement

All Rights Reserved

Audience

Faculty

Download

Share

COinS
 
May 29th, 4:00 PM May 29th, 5:00 PM

Leveraging AI for Grading and Feedback: Evaluating ChatGPT's Role in Academic Assessm

Universal Center

This study evaluates ChatGPT's ability to grade and provide feedback on student responses to an open-ended, constructed, and computational college-level physics exam question by comparing its performance to that of human content experts. Thirty student responses are graded by four experts using an evolving rubric, which is later applied by ChatGPT for scoring and feedback. Preliminary analysis of 10 responses demonstrates strong alignment between ChatGPT and human graders across total scores, performance group distinctions, and rubric criteria. These findings highlight ChatGPT's potential as a valuable tool for improving the efficiency and consistency of educational assessments.