Prompts Matter: Comparing ML/GAI Approaches for Generating Inductive Qualitative Coding Results

TL;DR

This study compares different ML and generative AI approaches for inductive qualitative coding, highlighting how instruction design impacts results and demonstrating the benefits of integrating human coding processes into AI prompts.

Contribution

It introduces and evaluates four ML/GAI approaches, including two novel, theory-informed methods, for qualitative coding in education research.

Findings

Significant discrepancies exist between ML/GAI approaches.

Theory-informed approaches outperform standard methods.

Incorporating human coding processes into prompts improves results.

Abstract

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.