Machine Intelligence and Human Intelligence: Exploring the Potentials of Machine Learning Based Approaches to Qualitative Survey Data Analysis
Bibliographic record
Abstract
This paper aims to explore new methods for qualitative data analysis in the digital age. We applied three machine learning (ML)-based methods—topic modelling via LDA and BERTopic, and generative AI-assisted inductive coding—in conjunction with the conventional thematic analysis method, to a set of qualitative data collected from a student survey over four years at a Canadian engineering school. The analysis processes as well as the outputs generated from the four methods were compared and evaluated against the trustworthiness criteria for quality in qualitative research. We observe that the ML-based approaches to analyzing qualitative survey data offer some levels of credibility and transferability while dependability and confirmability vary by method; and human intelligence of researchers needs to be involved to enhance the quality of ML-based analysis. Moving forward, we recommend a human-AI collaborative approach that combines ML-based inductive coding and human intelligence-based deductive coding processes. This new approach can facilitate and accelerate qualitative research and foster cross-disciplinary collaboration in 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 | 0.233 | 0.349 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.018 | 0.012 |
| Science and technology studies | 0.004 | 0.021 |
| Scholarly communication | 0.013 | 0.015 |
| Open science | 0.004 | 0.010 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
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.
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".