MétaCan
Menu
Back to cohort
Record W4360978668 · doi:10.1145/3581754.3584136

Supporting Qualitative Analysis with Large Language Models: Combining Codebook with GPT-3 for Deductive Coding

2023· preprint· en· W4360978668 on OpenAlexaff
Ziang Xiao, Xingdi Yuan, Q. Vera Liao, Rania Abdelghani, Pierre-Yves Oudeyer

Bibliographic record

Venuenot available
Typepreprint
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsMicrosoft (Canada)Research Canada
Fundersnot available
KeywordsCodebookGeneralizability theoryComputer scienceCoding (social sciences)Task (project management)Natural language processingCuriosityQualitative analysisQualitative researchTask analysisArtificial intelligenceQualitative propertyMachine learningData sciencePsychologySocial psychology

Abstract

fetched live from OpenAlex

Qualitative analysis of textual contents unpacks rich and valuable information by assigning labels to the data. However, this process is often labor-intensive, particularly when working with large datasets. While recent AI-based tools demonstrate utility, researchers may not have readily available AI resources and expertise, let alone be challenged by the limited generalizability of those task-specific models. In this study, we explored the use of large language models (LLMs) in supporting deductive coding, a major category of qualitative analysis where researchers use pre-determined codebooks to label the data into a fixed set of codes. Instead of training task-specific models, a pre-trained LLM could be used directly for various tasks without fine-tuning through prompt learning. Using a curiosity-driven questions coding task as a case study, we found, by combining GPT-3 with expert-drafted codebooks, our proposed approach achieved fair to substantial agreements with expert-coded results. We lay out challenges and opportunities in using LLMs to support qualitative coding and beyond.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.057
metaresearch head score (Gemma)0.325
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesnone
DomainCandidate signal: Methods · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.943
Threshold uncertainty score0.302

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0570.325
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0010.002
Bibliometrics0.0050.004
Science and technology studies0.0020.004
Scholarly communication0.0070.010
Open science0.0050.013
Research integrity0.0020.005
Insufficient payload (model declined to judge)0.0100.006

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.090
GPT teacher head0.390
Teacher spread0.301 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

Study designSimulation or modeling
DomainMethods
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations207
Published2023
Admission routes1
Has abstractyes

Explore more

Same topicTopic ModelingFrench-language works237,207