Formally comparing topic models and human-generated qualitative coding of physician mothers’ experiences of workplace discrimination
Bibliographic record
Abstract
Differences between computationally generated and human-generated themes in unstructured text are important to understand yet difficult to assess formally. In this study, we bridge these approaches through two contributions. First, we formally compare a primarily computational approach, topic modeling, to a primarily human-driven approach, qualitative thematic coding, in an impactful context: physician mothers’ experience of workplace discrimination. Second, we compare our chosen topic model to a principled alternative topic model to make explicit study design decisions meriting consideration in future research. By formally contrasting computationally generated (i.e. topic modeling) and human-generated (i.e. thematic coding) knowledge, we shed light on issues of interest to several audiences, notably computational social scientists who wish to understand study design tradeoffs, and qualitative researchers who may wish to leverage computational methods to improve the speed and reproducibility of labor-intensive coding. Although useful in other domains, we highlight the value of fast, reproducible methods to better understand experiences of workplace discrimination.
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 | 0.112 | 0.405 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.002 | 0.006 |
| Scholarly communication | 0.007 | 0.006 |
| Open science | 0.003 | 0.004 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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".