Examples
Worked examples
- Is an instance
Using an LLM to generate an initial set of candidate codes from a batch of interview transcripts, which two human researchers then independently refine and apply
- Is an instance
Using AI-assisted coding as one of several coders in an inter-rater reliability design, with disagreements adjudicated by a human
Counter-examples
Looks similar, but isn't
- Not an instance
Using a word-frequency or keyword-count tool with no learned model behind it is basic text analysis, not AI-assisted coding in this sense
- Not an instance
An AI tool used only to transcribe audio to text is transcription, not coding -- coding is the subsequent interpretive step
Editorial commentary
AI in qualitative coding refers specifically to using generative AI to perform the interpretive act of coding — assigning conceptual labels to segments of qualitative data — not to transcription, translation, or general text processing that happens before or after coding.
Why the risk profile is distinct
Three concerns recur in the methodological literature on this practice. First, confidentiality: qualitative data frequently contains identifiable or sensitive participant disclosures, and uploading raw transcripts to a third-party AI service can breach the terms of the informed consent under which the data was collected — see informed consent in research, and confirm with an IRB/REC whether a study’s consent language and data-use agreements actually permit this before doing it. Second, interpretive validity: qualitative coding is traditionally grounded in a researcher’s sustained immersion in the data and disciplinary theory; an AI system applying superficial pattern-matching can miss context, sarcasm, or culturally specific meaning, and can also silently reproduce whatever biases are latent in its training data when categorising human speech. Third, inter-coder reliability statistics (e.g. Cohen’s kappa) were designed to quantify agreement between human coders reasoning independently; applying the same statistic to AI-vs-human agreement doesn’t measure the same construct, since the AI coder isn’t a second independent interpretive perspective in the way a second trained human is.
How this differs from related AI-band terms
- vs. AI summarisation: coding assigns structured labels against a codebook; summarisation produces free-text condensation with no fixed coding scheme.
- vs. AI in literature search: coding operates on a study’s own primary data; literature search operates on the secondary literature.
Disclosure practice
Where AI materially assisted or performed coding, current guidance (ICMJE, COPE) calls for reporting this in Methods: which tool and version, what role it played (first-pass triage vs. sole coder), and what human verification step followed — see AI tool disclosure and prompt engineering for recording the exact prompts used, which matters for anyone attempting to reproduce the coding.
Also known as
LLM coding (qualitative) · AI-assisted thematic analysis
Machine-readable encodings
Use in your systems
<role vocab="credit"
vocab-identifier="https://casrai.org/dictionary/"
vocab-term="AI in qualitative coding"
vocab-term-identifier="https://casrai.org/dictionary/term/ai-in-qualitative-coding" />{
"@context": "https://schema.org",
"@type": "DefinedTerm",
"@id": "https://casrai.org/dictionary/term/ai-in-qualitative-coding",
"name": "AI in qualitative coding",
"identifier": "https://casrai.org/dictionary/term/ai-in-qualitative-coding",
"description": "The use of an LLM or other AI tool to assign codes, categories, or themes to qualitative data -- interview transcripts, open-ended survey responses, field notes -- either as a first-pass triage that a human coder then reviews, or, more controversially, as a sole or primary coder alongside or instead of a human.",
"inDefinedTermSet": "https://casrai.org/dictionary/domain/genai-disclosure#set",
"url": "https://casrai.org/dictionary/term/ai-in-qualitative-coding",
"sameAs": [
"LLM coding (qualitative)",
"AI-assisted thematic analysis"
],
"license": "https://creativecommons.org/licenses/by/4.0/",
"publisher": {
"@id": "https://casrai.org/#organization"
},
"author": {
"@id": "https://casrai.org/#editorial-team"
},
"datePublished": "2026-05-21T01:57:07",
"dateModified": "2026-08-22T14:51:47",
"inLanguage": "en-GB",
"isAccessibleForFree": true
}
