Rapid advancements in generative artificial intelligence (AI), specifically large language models (LLMs), offer unprecedented opportunities and challenges for qualitative researchers. This paper presents comprehensive guidelines for the ethical and effective use of LLMs in the development and refinement of interview protocols. Through a multidisciplinary lens, this paper explores potential pitfalls, ethical considerations, and best practices to ensure the responsible integration of LLMs in the research process. The guidelines proposed serve not only as a methodological roadmap for researchers but also as a catalyst for dialogue on the ethical dimensions of LLMs in qualitative research. Furthermore, the authors describe and share a web-based application developed to guide users through the stages of the protocol. Ultimately, the paper calls for a collective, informed approach to harness the capabilities of LLMs while upholding the integrity and ethical standards of scholarly research.
Keywords
large language models, ChatGPT, qualitative research, interview protocol refinement framework, interview protocol, generative artificial intelligence
Author Bio(s)
Dr. Jessica Parker is a researcher and educator who is passionate about demystifying the research and writing process for scholars. She is the founder and CEO of Dissertation by Design and the co-founder of Academic Insight Lab. Her research interests are at the intersection of technology and education; she is particularly intrigued by the potential of generative AI for academic purposes, exploring how this technology can revolutionize the way we conduct research, teach, and learn. Jessica has worked with a diverse range of researchers and scholars and continues to teach doctoral students of Health Sciences at Massachusetts College of Pharmacy and Health Sciences (MCPHS) University. Please direct correspondence to jessica.parker@mcphs.edu.
Dr. Veronica Richard is a qualitative methodologist at Dissertation by Design. She has held various academic positions, including adjunct, assistant, and associate professor roles at the University of Northern Colorado, Indiana University Northwest, and Concordia University Chicago. Her experience spans working with undergraduate, master’s, and doctoral students, primarily in the fields of literacy and research methods. Throughout her career, Veronica has been an integral part of nine research teams, many of which were grant-funded and dedicated to supporting at-risk youth. Veronica earned her Ph.D. from the University of Northern Colorado in 2010, specializing in Applied Statistical Research and Research Methods with a cognate in Reading. Please direct correspondence to veronica@dissertationbydesign.com.
Dr. Kimberly Becker is an applied linguist who specializes in disciplinary academic writing and English for research publication purposes. She is the co-founder of Academic Insight Lab and holds a Ph.D. in applied linguistics and technology (Iowa State University, 2022) and an M.A. in teaching English as a second language (Northern Arizona University, 2004). Kimberly’s research and teaching experience as a professor and communication consultant has equipped her to support native and non-native English speakers in written, oral, visual, and electronic communication. Her most recent publications are related to the use of ethical AI for automated writing evaluation and a co-authored e-book, Preparing to Publish, about composing academic research manuscripts. Please direct correspondence to kimberly@academicinsightlab.org.
Acknowledgements
In the development of this manuscript, we employed GPT-4, a generative artificial intelligence model, as a collaborative tool. GPT-4 was instrumental in various stages of the research and writing process, including brainstorming, table construction, and the creation of example scenarios.
Parker, J. L.,
Richard, V. M.,
&
Becker, K.
(2023).
Guidelines for the Integration of Large Language Models in Developing and Refining Interview Protocols.
The Qualitative Report,
28(12), 3460-3474.
https://doi.org/10.46743/2160-3715/2023.6801
