A validity evaluation of lexicon‐based sentiment analysis of medical students' clinical performance from in‐training evaluation reports
Medical Education · 2026
DOI: 10.1111/medu.70101 ↗Kurz gefasst
Validierungsstudie in der Zeitschrift Medical Education, 2026. Verfasst von Irene Ma und 6 weiteren Autor:innen. Beteiligte Einrichtung: Office of Undergraduate Medical Education, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada. Hauptthemen laut MEDLINE: Students, Medical, Natural Language Processing, Clinical Competence, Educational Measurement. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Introduction
Assessment of clinical performance has traditionally been a numbers game based upon Likert scale ratings. But, thanks to advances in the science of natural language processing (NLP), it is now possible to incorporate rich narrative data into assessment. In this study, our objective was to evaluate the validity of lexicon‐based sentiment analysis of medical students' clinical performance from in‐training evaluation reports (ITERs) with a view to fully integrating this as a machine‐based process into future assessment decisions.
Methods
This was a mixed methods, retrospective derivation/validation cohort study structured around Kane's validity framework. We used content analysis to create a lexicon of performance descriptors, performed a G‐study, and calculated the positive likelihood ratio (LR+) for descriptors ( scoring ). To evaluate generalisation , we calculated the intraclass correlation coefficient and compared descriptors in derivation and validation cohorts. We then performed [human] lexicon‐based sentiment analysis and compared the number of descriptors of different types between cohorts of highest performing students (HPS) and lowest performing students (LPS).
Results
In our G‐study, 86.6% of variance was attributed to the student. The ICC between raters for identification of descriptors was 0.93. The mean number of neutral descriptors was similar between HPS and LPS cohorts, but the number of negative descriptors was higher for LPS (11.4 (10.8) versus 1.4 (1.6) for HPS, p < 0.01, d = 1.37) and the number of positive descriptors was higher for HPS (19 (14) versus 1.4 (1.5) for LPS, p < 0.001, d = 1.86).
Discussion
In the midst of their busy clinical work schedule, preceptors find time to tell a story about a medical student and these narrative data enrich the assessment portfolio. Based upon our validity argument, we feel there is a role for lexicon‐based sentiment analysis of clinical performance descriptors in ITERs and that these results can contribute meaningfully to assessment decisions.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Office of Undergraduate Medical Education, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada.
ORCID-Profile: Mike Paget, Janeve Desy
Zitieren
APA
Ma, I., Paget, M., Desy, J., Harvey, A., Bendiak, G., Naugler, C., & McLaughlin, K. (2026). A validity evaluation of lexicon‐based sentiment analysis of medical students' clinical performance from in‐training evaluation reports. Medical Education. https://doi.org/10.1111/medu.70101
Vancouver
Ma I, Paget M, Desy J, Harvey A, Bendiak G, Naugler C, et al. A validity evaluation of lexicon‐based sentiment analysis of medical students' clinical performance from in‐training evaluation reports. Medical Education. 2026. doi:10.1111/medu.70101
BibTeX
@article{Ma2026,
author = {Ma, Irene and Paget, Mike and Desy, Janeve and Harvey, Adrian and Bendiak, Glenda and Naugler, Christopher and McLaughlin, Kevin},
title = {A validity evaluation of lexicon‐based sentiment analysis of medical students' clinical performance from in‐training evaluation reports},
journal = {Medical Education},
year = {2026},
doi = {10.1111/medu.70101}
}
EUVIMED