Prompts Matter: Comparing ML/GAI Approaches for Generating Inductive Qualitative Coding Results
This work addresses the time-intensive nature of inductive qualitative coding in education research, offering incremental improvements through prompt design.
The study tackled the problem of generating inductive qualitative coding results using ML/GAI approaches by comparing known and novel methods on an online community dataset, finding significant discrepancies and advantages for approaches that incorporate human coding processes into prompts.
Inductive qualitative methods have been a mainstay of education research for decades, yet it takes much time and effort to conduct rigorously. Recent advances in artificial intelligence, particularly with generative AI (GAI), have led to initial success in generating inductive coding results. Like human coders, GAI tools rely on instructions to work, and how to instruct it may matter. To understand how ML/GAI approaches could contribute to qualitative coding processes, this study applied two known and two theory-informed novel approaches to an online community dataset and evaluated the resulting coding results. Our findings show significant discrepancies between ML/GAI approaches and demonstrate the advantage of our approaches, which introduce human coding processes into GAI prompts.