MétaCan
Menu
Back to cohort
Record W4402163574 · doi:10.37074/jalt.2024.7.2.32

Exploring the synergy of human and AI-driven approaches in thematic analysis for qualitative educational research

2024· article· en· W4402163574 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

VenueJournal of Applied Learning & Teaching · 2024
Typearticle
Languageen
FieldSocial Sciences
TopicComputational and Text Analysis Methods
Canadian institutionsUniversity of Calgary
FundersTD Bank
KeywordsThematic analysisQualitative researchQualitative analysisThematic mapSociologyPsychologyComputer scienceGeographySocial scienceCartography

Abstract

fetched live from OpenAlex

This paper investigates the integration of Generative Artificial Intelligence (GenAI), particularly Large Language Models (LLMs) such as GPT-4, into qualitative analysis in educational research. Utilizing TRACER (Transcript Analysis and Concept Extraction Resource), a GenAI-driven tool, the study evaluated its efficiency, reproducibility, and synergy with human analytical expertise. The research demonstrated that TRACER significantly streamlined thematic analysis, efficiently handled large data volumes, and maintained consistency in theme identification. The findings reveal that integrating TRACER’s computational power with human interpretive skills enriches research outcomes, suggesting a collaborative approach for optimal results. Despite its efficacy, limitations such as data scope and current GenAI capabilities are acknowledged, indicating areas for future development. This paper contributes to the understanding of GenAI’s role in qualitative research, proposing it as a valuable tool for overcoming traditional challenges in the field and highlighting the importance of human-AI collaboration for comprehensive and nuanced analyses in educational research.

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)0.018
metaresearch head score (Gemma)0.001
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: Empirical
Teacher disagreement score0.299
Threshold uncertainty score0.630

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0180.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0010.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.001
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 head0.493
GPT teacher head0.528
Teacher spread0.035 · 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