AI-Assisted Grading and Personalized Feedback in Large Political Science Classes

Results from Randomized Controlled Trials

Artificial Intelligence
Political Science Education
Randomized Controlled Trials

Heinrich, Tobias, Spencer Baily, Kuan-wu Chen, Jack DeOliveira, Sanghoon Park, and Navida Chun-han Wang. 2025. “AI-Assisted Grading and Personalized Feedback in Large Political Science Classes: Results from Randomized Controlled Trials.” PLOS One: forthcoming.

Authors
Affiliations

Department of Political Science, The University of Houston, Houston, Texas, United States of America

Political Science, Univeristy of South Carolina

Kuan-wu Chen

Institute of Political Science, Academia Sinica, Taipei, Taiwan

Jack DeOliveira

Political Science, Univeristy of South Carolina

Political Science, Univeristy of South Carolina

Navida Chun-han Wang

Department of Political Science, University of Michigan, Ann Arbor, Michigan, United States of America

Published

July 2025

Abstract

Grading and providing personalized feedback on short-answer questions is time consuming. Professional incentives often push instructors to rely on multiple-choice assessments instead, reducing opportunities for students to develop critical thinking skills. Using large-language-model (LLM) assistance, we augment the productivity of instructors grading short-answer questions in large classes. Through a randomized controlled trial across four undergraduate courses and almost 300 students in 2023/2024, we assess the effectiveness of AI-assisted grading and feedback in comparison to human grading. Our results demonstrate that AI-assisted grading can mimic what an instructor would do in a small class.