Natural language is a vital source of evidence for the social sciences. Yet quantifying large volumes of text rigorously and precisely is extremely difficult, and automated methods have struggled to match the “gold standard” of human coding. The present work used GPT-4 to conduct an automated analysis of 1,356 essays, rating the authors’ spirituality on a continuous scale. This presents an especially challenging test for automated methods, due to the subtlety of the concept and the difficulty of inferring complex personality traits from a person’s writing. Nonetheless, we found that GPT-4’s ratings demonstrated excellent internal reliability, remarkable consistency with a human rater, and strong correlations with self-report measures and behavioral indicators of spirituality. These results suggest that, even on nuanced tasks requiring a high degree of conceptual sophistication, automated text analysis with Generative Pre-trained Transformers can match human-level performance. Hence, these results demonstrate the extraordinary potential for such tools to advance social scientific research.
osf.io/preprints/psyarxiv/bqnmk/
Professor at George Washington University
I am a Professor with Human-Technology Collaboration and Educational Technology programs at George Washington University in Washington DC. I have written 12 books and more than 100 articles, and I co-host of the Parsing Science podcast where scientists tell the stories behind their research. I am also the developer of the WeShareScience.com online platform for sharing research videos, and SciencePods.com where researchers can create free podcasts about their science. My research interests include human interactions with intelligent machines, needs, needs assessments, and instructional design.
Latest posts by Ryan Watkins (see all)