The applicability of LLMs to qualitative data analysis is obvious. Analyzing and making sense of large amounts of textual data is what they’re made for. But there are risks, and there is a heated debate in the qualitative research community over whether AI should be used at all in QDA.
This module takes you through both sides of the debate and describes:
Where AI fits (and doesn't fit) in the qualitative analysis process
General-purpose LLMs vs. dedicated QDA platforms like ATLAS.ti, MAXQDA, and newer AI-native tools
How to use AI for deductive and inductive thematic analysis, with practical prompt examples
A best-practice workflow with built-in quality checkpoints
How to verify AI-generated codes and themes before building on them
Despite the opposition, the reality is that AI will certainly become more and more commonly used in QDA. It will not only make the data analysis process more efficient, it will also make it possible to analyze large amounts of data that now go unanalyzed - think qualitative observations in health worker supervision reports. It’s best we learn how to use these tools as effectively and responsibly as possible.
