2026 ASEE Annual Conference & Exposition

This research paper explores the use of generative artificial intelligence (AI) tools to support qualitative coding in engineering education research. The purpose of qualitative analysis is to generate meaning from rich, descriptive data. However, qualitative analysis can be both labor-intensive and time-consuming, especially when working with large or complex data sets. The process of meaning-making occurs through active engagement with the data, where researchers develop insights by identifying themes, patterns, and relationships. While this labor is central to the qualitative process, the growing prevalence of generative AI tools in research and society presents opportunities to reconsider how such tools might support, not replace, this important work.

Generative AI tools, such as large language models, have the potential to reduce some of the manual effort involved in qualitative coding, organization, and synthesis. Yet, their use raises critical questions about ethics, validity, transparency, and the preservation of researcher interpretation. To be equipped to use these tools ethically and effectively, qualitative researchers must understand both their benefits and limitations. This study seeks to explore how generative AI can be integrated responsibly into the qualitative analysis process and to document what we learn through that experience.

This research paper presents a practical guide for novice researchers who wish to experiment with using AI tools to support qualitative research. It details several “tricks of the trade” and strategies for effectively combining human expertise with AI-assisted processes. While prior work has used AI to assist in coding, transcription, and data organization, this study contributes a grounded perspective on using AI as a collaborative partner rather than a replacement for human interpretation. Importantly, we acknowledge that AI in its current form cannot replicate the depth of understanding that emerges through a researcher’s sustained engagement with qualitative data. Our work emphasizes that critical thinking and reflexivity remain central to the research process.

This paper documents our process of integrating AI into the qualitative coding of first-year engineering students’ reflections. These reflections were drawn from end-of-year assignments in a two-semester introductory engineering course at a large, public, mid-Atlantic research-focused university. We describe lessons learned during this process, the benefits and challenges encountered, and the ethical boundaries necessary for responsible AI use in qualitative analysis.