Analyzing Undergraduate Problem-Solving in Physics Through Interaction With an AI Chatbot

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Hashmi, Syed Furqan Abbas, Rebello, N. Sanjay
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918127915237376
author Hashmi, Syed Furqan Abbas
Rebello, N. Sanjay
author_facet Hashmi, Syed Furqan Abbas
Rebello, N. Sanjay
contents Providing individualized scaffolding for physics problem solving at scale remains an instructional challenge. We investigate (1) students' perceptions of a Socratic Artificial Intelligence (AI) chatbot's impact on problem-solving skills and confidence and (2) how the specificity of students' questions during tutoring relates to performance. We deployed a custom Socratic AI chatbot in a large-enrollment introductory mechanics course at a Midwestern public university, logging full dialogue transcripts from 150 first-year STEM majors. Post-interaction surveys revealed median ratings of 4.0/5 for knowledge-based skills and 3.4/5 for overall effectiveness. Transcript analysis showed question specificity rose from approximately 10-15% in the first turn to 100% by the final turn, and specificity correlated positively with self reported expected course grade (Pearson r = 0.43). These findings demonstrate that AI-driven Socratic dialogue not only fosters expert-like reasoning but also generates fine-grained analytics for physics education research, establishing a scalable dual-purpose tool for instruction and learning analytics.
format Preprint
id arxiv_https___arxiv_org_abs_2508_14778
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Analyzing Undergraduate Problem-Solving in Physics Through Interaction With an AI Chatbot
Hashmi, Syed Furqan Abbas
Rebello, N. Sanjay
Physics Education
Providing individualized scaffolding for physics problem solving at scale remains an instructional challenge. We investigate (1) students' perceptions of a Socratic Artificial Intelligence (AI) chatbot's impact on problem-solving skills and confidence and (2) how the specificity of students' questions during tutoring relates to performance. We deployed a custom Socratic AI chatbot in a large-enrollment introductory mechanics course at a Midwestern public university, logging full dialogue transcripts from 150 first-year STEM majors. Post-interaction surveys revealed median ratings of 4.0/5 for knowledge-based skills and 3.4/5 for overall effectiveness. Transcript analysis showed question specificity rose from approximately 10-15% in the first turn to 100% by the final turn, and specificity correlated positively with self reported expected course grade (Pearson r = 0.43). These findings demonstrate that AI-driven Socratic dialogue not only fosters expert-like reasoning but also generates fine-grained analytics for physics education research, establishing a scalable dual-purpose tool for instruction and learning analytics.
title Analyzing Undergraduate Problem-Solving in Physics Through Interaction With an AI Chatbot
topic Physics Education
url https://arxiv.org/abs/2508.14778