A Comparison of Machine-Graded (ChatGPT) and Human-Graded Essay Scores in Veterinary Admissions

Abstract

Admissions committees have historically emphasized cognitive measures, but a paradigm shift toward holistic reviews now places greater importance on non-cognitive skills. These holistic reviews may include personal statements, experiences, references, interviews, multiple mini-interviews, and situational judgment tests, often requiring substantial faculty resources. Leveraging advances in artificial intelligence, particularly in natural language processing, this study was conducted to assess the agreement of essay scores graded by both humans and machines (OpenAI's ChatGPT). Correlations were calculated among these scores and cognitive and non-cognitive measures in the admissions process. Human-derived scores from 778 applicants in 2021 and 552 in 2022 had item-specific inter-rater reliabilities ranging from 0.07 to 0.41, while machine-derived inter-replicate reliabilities ranged from 0.41 to 0.61. Pairwise correlations between human- and machine-derived essay scores and other admissions criteria revealed moderate correlations between the two scoring methods (0.41) and fair correlations between the essays and the multiple mini-interview (0.20 and 0.22 for human and machine scores, respectively). Despite having very low correlations, machine-graded scores exhibited slightly stronger correlations with cognitive measures (0.10 to 0.15) compared to human-graded scores (0.01 to 0.02). Importantly, machine scores demonstrated higher precision, approximately two to three times greater than human scores in both years. This study emphasizes the importance of careful item design, rubric development, and prompt formulation when using machine-based essay grading. It also underscores the importance of employing replicates and robust statistical analyses to ensure equitable applicant ranking when integrating machine grading into the admissions process.