EUVIMEDEUVIMED entdecken
Randomisierte kontrollierte StudieOpen Access · CC BY 4.0

AI-assisted grading and personalized feedback in large political science classes: Results from randomized controlled trials

Tobias Heinrich iD, Spencer Baily iD, Kuan-Wu Chen, Jack DeOliveira, Sanghoon Park iD, Navida Chun-Han Wang

PLOS One · 2025

DOI: 10.1371/journal.pone.0328041 ↗

Kurz gefasst

Randomisierte kontrollierte Studie in der Zeitschrift PLOS One, 2025. Verfasst von Tobias Heinrich und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Political Science, The University of Houston, Houston, Texas, United States of America. Hauptthemen laut MEDLINE: Educational Measurement, Artificial Intelligence, Politics, Science. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Educational MeasurementArtificial IntelligencePoliticsScienceHumansStudentsMaleFemaleFeedback

Autor:innen und Institutionen

  • Department of Political Science, The University of Houston, Houston, Texas, United States of America.
  • Department of Political Science, University of South Carolina, Columbia, South Carolina, United States of America.
  • Institute of Political Science, Academia Sinica, Taipei, Taiwan.
  • Kangwon Institute of Unification Studies, Kangwon National University, Chuncheon, Gangwon, Republic of Korea.
  • Department of Political Science, University of Michigan, Ann Arbor, Michigan, United States of America.

ORCID-Profile: Tobias Heinrich, Spencer Baily, Sanghoon Park

Zitieren

APA

Heinrich, T., Baily, S., Chen, K. W., DeOliveira, J., Park, S., & Wang, N. C. (2025). AI-assisted grading and personalized feedback in large political science classes: Results from randomized controlled trials. PLOS One. https://doi.org/10.1371/journal.pone.0328041

Vancouver

Heinrich T, Baily S, Chen KW, DeOliveira J, Park S, Wang NC. AI-assisted grading and personalized feedback in large political science classes: Results from randomized controlled trials. PLOS One. 2025. doi:10.1371/journal.pone.0328041

BibTeX
@article{Heinrich2025,
  author = {Heinrich, Tobias and Baily, Spencer and Chen, Kuan-Wu and DeOliveira, Jack and Park, Sanghoon and Wang, Navida Chun-Han},
  title = {AI-assisted grading and personalized feedback in large political science classes: Results from randomized controlled trials},
  journal = {PLOS One},
  year = {2025},
  doi = {10.1371/journal.pone.0328041}
}
Kostenlos starten →