Proof of Concept: Leveraging Large Language Models for Qualitative Analysis of Participant Feedback

Authors

Andrew B. Crocker, Texas A&M AgriLife Extension Service, Texas A&M SystemFollow
Marcelo Schmidt, Texas Tech University - School of Veterinary MedicineFollow
Juan Diego Tejeda, Texas Tech University - School of Veterinary MedicineFollow
Howard Rodriguez-Mori, Texas Tech University - School of Veterinary MedicineFollow

Volume

63

Issue

1

Abstract

This proof-of-concept study explores the innovative application of Large Language Models (LLMs) for qualitative analysis of feedback from an Extension program, addressing the challenge of efficiently analyzing qualitative data. The study juxtaposes traditional human-led qualitative analysis with Artificial Intelligence (AI)-driven techniques, revealing the complementary strengths of human insights and AI efficiency. It underscores the potential of LLMs to enhance qualitative analysis while recognizing the need for human oversight to ensure depth and context accuracy. This research contributes to the fields of program evaluation and data analysis, offering a new paradigm for integrating advanced AI tools in qualitative research.

Creative Commons License

This work is licensed under a Creative Commons Attribution-Noncommercial-Share Alike 4.0 License.

Recommended Citation

Crocker, A. B., Schmidt, M., Tejeda, J. D., & Rodriguez-Mori, H. (2025). Proof of Concept: Leveraging Large Language Models for Qualitative Analysis of Participant Feedback. The Journal of Extension, 63(1), Article 16. https://open.clemson.edu/joe/vol63/iss1/16