Can ChatGPT Perform a Grounded Theory Approach to Do Risk Analysis? An Empirical Study
Bibliographic record
Abstract
Grounded theory is a widely used scientific method for generating theories from qualitative data analysis. However, it is often time-consuming and requires professional training. Generative artificial intelligence, such as ChatGPT, excels in understanding and analyzing text, making it a valuable tool for qualitative research. This research proposes a novel approach to guide ChatGPT using the grounded theory method for qualitative data analysis and to design rigorous metrics for evaluating its performance. Using risk analysis as a case study, we compare ChatGPT’s results with those obtained through manual methods. Our findings show that, with expert guidance, ChatGPT can effectively perform the grounded theory method, achieving results comparable to those of human analysts. To maximize its potential, researchers should properly guide ChatGPT in performing required tasks, rigorously evaluate its outputs, and ensure high-quality results. This approach can significantly enhance the efficiency and quality of qualitative data analysis.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.156 | 0.352 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.004 |
| Science and technology studies | 0.003 | 0.005 |
| Scholarly communication | 0.006 | 0.014 |
| Open science | 0.004 | 0.007 |
| Research integrity | 0.002 | 0.004 |
| Insufficient payload (model declined to judge) | 0.008 | 0.002 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".