Students' Perceptions to a Large Language Model's Generated Feedback and Scores of Argumentation Essays

TL;DR

This study explores the use of GPT-4o to provide AI-generated feedback on students' scientific arguments in physics, aiming to improve problem-solving skills and metacognition in large classes.

Contribution

It demonstrates the feasibility and student perceptions of AI-generated feedback for scientific argumentation in large physics courses.

Findings

Students found AI feedback useful and accurate

AI feedback has potential to support large-enrollment physics education

The approach enhances students' problem-solving and metacognitive skills

Abstract

Students in introductory physics courses often rely on ineffective strategies, focusing on final answers rather than understanding underlying principles. Integrating scientific argumentation into problem-solving fosters critical thinking and links conceptual knowledge with practical application. By facilitating learners to articulate their scientific arguments for solving problems, and by providing real-time feedback on students' strategies, we aim to enable students to develop superior problem-solving skills. Providing timely, individualized feedback to students in large-enrollment physics courses remains a challenge. Recent advances in Artificial Intelligence (AI) offer promising solutions. This study investigates the potential of AI-generated feedback on students' written scientific arguments in an introductory physics class. Using Open AI's GPT-4o, we provided delayed feedback on student written scientific arguments and surveyed them about the perceived usefulness and accuracy of this feedback. Our findings offer insights into the viability of implementing real-time AI feedback to enhance students' problem-solving and metacognitive skills in large-enrollment classrooms.