Performance of automated and manual coding systems for occupational data: A case study of historical records
Bibliographic record
Abstract
BACKGROUND: Occupational data are a common source of workplace exposure and socioeconomic information in epidemiologic research. We compared the performance of two occupation coding methods, an automated software and a manual coder, using occupation and industry titles from U.S. historical records. METHODS: We collected parental occupational data from 1920-40s birth certificates, Census records, and city directories on 3,135 deceased individuals in the Atherosclerosis Risk in Communities (ARIC) study. Unique occupation-industry narratives were assigned codes by a manual coder and the Standardized Occupation and Industry Coding software program. We calculated agreement between coding methods of classification into major Census occupational groups. RESULTS: Automated coding software assigned codes to 71% of occupations and 76% of industries. Of this subset coded by software, 73% of occupation codes and 69% of industry codes matched between automated and manual coding. For major occupational groups, agreement improved to 89% (kappa = 0.86). CONCLUSIONS: Automated occupational coding is a cost-efficient alternative to manual coding. However, some manual coding is required to code incomplete information. We found substantial variability between coders in the assignment of occupations although not as large for major groups.
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 | 0.089 | 0.312 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.004 |
| Science and technology studies | 0.003 | 0.002 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".