Research case
Codebooks and GPT-3 for deductive coding (Xiao et al., IUI 2023 Companion)
A case study combines expert-written codebooks with GPT-3 prompts for coding curiosity-driven questions, then compares labels with expert coding.
What is reported
The model reached fair-to-substantial agreement (Cohen's kappa) with experts, enough for the authors to call codebook-guided LLM coding feasible.
Before you use it
Deductive coding with a fixed codebook only; inductive, interpretive work was not tested. Newer models perform differently.
Sources and review
Source checked · Not tested by this site
Checked the public abstract and bibliographic record. Results describe the authors' study, not a replication by this site.
License and reuse
No license has been recorded. Check the source’s license before reusing code, models or data.
A license note is not a license audit. Open source does not guarantee free hosting, model access or commercial reuse.