MétaCan
Menu
Back to cohort
Record W4411268843 · doi:10.22318/icls2025.322165

Qualitative Research in the Age of LLMs: A Human-in-the-Loop Approach to Hybrid Thematic Analysis

2025· article· en· W4411268843 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueProceedings. · 2025
Typearticle
Languageen
FieldSocial Sciences
TopicLegal Education and Practice Innovations
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsThematic mapThematic analysisComputer scienceLoop (graph theory)Qualitative researchSociologyGeographySocial scienceMathematicsCartography

Abstract

fetched live from OpenAlex

This paper introduces a hybrid (deductive-inductive) human-in-the-loop (HHitL) framework for thematic analysis (TA), leveraging large language models (LLMs) while prioritizing human interpretation and decision-making.Grounded in reflexive TA, our resulting six-stage framework is guided by design principles of interoperability, human-LLM transactivity, scalability, and transparency.This method enables mixed-methods displays (e.g., network graphs, code frequency/diversity/magnitude metrics) supporting productive data triangulation.We demonstrate this HHitL-TA approach by analyzing engineering students' motivations based on Social Cognitive Career Theory (SCCT), illustrating the framework's application, principles, and triangulation potential.While acknowledging potential risks, the HHitL design actively mitigates passive researcher roles through transactivity and transparency, promoting humans as generative, active directors of the analysis.This work contributes a structured methodology for rigorous, scalable qualitative inquiry using LLMs.

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.015
metaresearch head score (Gemma)0.003
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Qualitative · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.713
Threshold uncertainty score0.642

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0150.003
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.011
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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 head0.357
GPT teacher head0.595
Teacher spread0.238 · 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