Validation of the Use of a Large Language Model for Detecting Sentiment in Student Course Evaluation
Family Medicine · 2026
DOI: 10.22454/fammed.2026.142029 ↗Kurz gefasst
Validierungsstudie in der Zeitschrift Family Medicine, 2026. Verfasst von Kate Rowland und 10 weiteren Autor:innen. Beteiligte Einrichtung: Rush University Medical Center, Chicago, IL. Hauptthemen laut MEDLINE: Natural Language Processing, Students, Medical. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background and Objectives: The use of large language models and natural language processing (NLP) in medical education has expanded rapidly in recent years. Because of the documented risks of bias and errors, these artificial intelligence (AI) tools must be validated before being used for research or education. Traditional and novel conceptual frameworks can be used. This study aimed to validate the application of an NLP method, bidirectional encoder representations from transformers (BERT) model, to identify the presence and patterns of sentiment in end-of-course evaluations from M3 (medical school year 3) core clerkships at multiple institutions.
Methods
We used the Patino framework, designed for the use of artificial intelligence in health professions education, as a guide for validating the NLP. Written comments from de-identified course evaluations at four schools were coded by teams of two human coders, and human-human interrater reliability statistics were calculated. Humans identified key terms to train the BERT model. The trained BERT model predicted the sentiments of a set of comments, and human-NLP interrater reliability statistics were calculated.
Results
A total of 364 discrete comments were evaluated in the human phase. The range of positive (30.6%–61.0%), negative (4.9%–39.5%), neutral (9.8%–19.0%), and mixed (1.7%–27.5%) sentiments varied by school. Human-human and human-AI interrater reliability also varied by school. Human-human and human-AI reliability were comparable.
Conclusions
Several conceptual frameworks offer models for validation of AI tools in health professions education. A BERT model, with training, can detect sentiment in medical student course evaluations with an interrater reliability similar to human coders.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Rush University Medical Center, Chicago, IL.
- Michigan State University, East Lansing, MI.
- University of Nebraska Medical Center, Omaha, NE.
- Department of Medical Education, University of Toledo, Toledo, OH.
- University of Kentucky, Lexington, KY.
- University of Kansas, Kansas City, KS.
Zitieren
APA
Rowland, K., Wang, L., Bash, K., DeShetler, L., Vick, S., Nguyen, E., Rogers-Johnson, M., Anderson, L., Sweet, M., Fasula, K., & Carter, S. (2026). Validation of the Use of a Large Language Model for Detecting Sentiment in Student Course Evaluation. Family Medicine. https://doi.org/10.22454/fammed.2026.142029
Vancouver
Rowland K, Wang L, Bash K, DeShetler L, Vick S, Nguyen E, et al. Validation of the Use of a Large Language Model for Detecting Sentiment in Student Course Evaluation. Family Medicine. 2026. doi:10.22454/fammed.2026.142029
BibTeX
@article{Rowland2026,
author = {Rowland, Kate and Wang, Ling and Bash, Kirstie and DeShetler, Lori and Vick, Sarah and Nguyen, Emma and Rogers-Johnson, Michelle and Anderson, Lauren and Sweet, Michelle and Fasula, Kimberly and Carter, Stefanie},
title = {Validation of the Use of a Large Language Model for Detecting Sentiment in Student Course Evaluation},
journal = {Family Medicine},
year = {2026},
doi = {10.22454/fammed.2026.142029}
}
EUVIMED