Document Type

Article

Publication Date

2025

Publication Title

The Journal of Applied Instruction Design

Volume

14

Issue

3

Pages

136-155

Abstract

This case examines the innovative use of Large Language Models (LLMs) to generate learner personas for developing learner-centered cybersecurity training materials when direct access to initial learner data is not available. The team developed a nine-stage iterative process for creating and refining AI-generated personas to address this constraint, integrating ethical review, stakeholder feedback, and action research principles. The process expanded upon Kouprie and Visser’s (2009) empathic design framework to ensure cultural responsiveness and mitigate potential biases in LLM outputs. Through multiple refinement cycles, initial generic personas evolved into detailed, context-rich archetypes which informed the development of effective and context-responsive training materials. The case demonstrates how AI-generated personas can serve as valuable tools for instructional design in emerging technical domains when developed through rigorous iterative processes and ethical oversight. This approach offers insights for educational initiatives facing similar challenges in understanding diverse learner needs before direct audience data becomes available.

Rights

© 2025 The Authors.

Published under the terms of the Creative Commons Attribution 4.0 International (CC BY 4.0).

Original Publication Citation

Lovett, N., Yang, M., Herman, K., Li, B., Sosonkina, M., Purwanto, W., Jiang, P., & Wu, M. H. (2025). Leveraging large language models to create learner personas for training design. The Journal of Applied Instruction Design, 14(3), 136-155. https://jaid.edtechbooks.org/jaid_14_3/fkuiqkevdr

ORCID

0000-0002-2124-4552 (Purwanto), 0009-0005-0223-397X (Sosonkina)

Download

Share

COinS