A classification system that organizes concepts into categories. In research, a predefined set of tags or codes used to systematically categorize qualitative data.
Definition: A classification system that organizes concepts into categories. In research, a predefined set of tags or codes used to systematically categorize qualitative data.
A taxonomy is a hierarchical classification system that organizes concepts, objects, or data into categories based on shared characteristics.
When analyzing qualitative data, a taxonomy is your predefined set of categories or tags. For example, when coding user feedback, your taxonomy might include:
A well-defined taxonomy:
A taxonomy defines categories. An ontology defines the relationships between those categories.
When using LLMs for thematic analysis, providing a strict taxonomy is critical. It prevents the model from inventing its own categories and ensures output aligns with your analysis framework.
A formal representation of the relationships between concepts in a domain. Goes beyond taxonomy to define how categories relate to each other.
Research focused on understanding the 'what' and 'why' through rich stories, observations, and context. Seeks depth of understanding rather than statistical measurement.
This term is referenced in the following articles:
The biggest mistake teams make with AI is treating it like a magic black box. Here is a complete, reliable workflow for using LLMs as research assistants while maintaining critical human oversight.
Transform interview transcripts and observation notes into actionable themes through systematic coding. The difference between an opinion and a finding is whether two people agree.
AI is fundamentally changing what research roles look like. Some purely executional positions are already disappearing. Understanding what LLMs actually are, and are not, determines whether you use them effectively or get replaced by someone who does.
Beyond basic prompting, there are techniques that dramatically improve AI reliability: structured communication, using notes over transcripts, treating models as a committee of raters, and understanding when RAG or fine-tuning makes sense.
Before you design a single screen, the structure of your content must make sense to users. Card sorting and tree testing are specialized techniques for designing and validating information architecture.