Prompting the Machine: Introducing an LLM Data Extraction Method for Social Scientists
Bibliographic record
Abstract
This research note addresses a methodological gap in the study of large language models (LLMs) in social sciences: the absence of standardized data extraction procedures. While existing research has examined biases and the reliability of LLM-generated content, the establishment of transparent extraction protocols necessarily precedes substantive analysis. The paper introduces a replicable procedural framework for extracting structured political data from LLMs via API, designed to enhance transparency, accessibility, and reproducibility. Canadian federal and Quebec provincial politicians serve as an illustrative case to demonstrate the extraction methodology, encompassing prompt engineering, output processing, and error handling mechanisms. The procedure facilitates systematic data collection across multiple LLM versions, enabling inter-model comparisons while addressing extraction challenges such as response variability and malformed outputs. The contribution is primarily methodological—providing researchers with a foundational extraction protocol adaptable to diverse research contexts. This standardized approach constitutes an essential preliminary step for subsequent evaluation of LLM-generated content, establishing procedural clarity in this methodologically developing research domain.
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 | 0.128 | 0.282 |
| Meta-epidemiology (narrow) | 0.001 | 0.002 |
| Meta-epidemiology (broad) | 0.001 | 0.003 |
| Bibliometrics | 0.010 | 0.007 |
| Science and technology studies | 0.003 | 0.004 |
| Scholarly communication | 0.011 | 0.012 |
| Open science | 0.004 | 0.014 |
| Research integrity | 0.003 | 0.005 |
| Insufficient payload (model declined to judge) | 0.008 | 0.006 |
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".