RegBR: A novel Brazilian government framework to classify and analyze industry-specific regulations
Bibliographic record
Abstract
Government transparency and openness are key factors to bring forth the modernization of the state. The combination of transparency and digital information has given rise to the concept of Open Government, that increases citizen understanding and monitoring of government actions, which in turn improves the quality of public services and of the government decision making process. With the goal of improving legislative transparency and the understanding of the Brazilian regulatory process and its characteristics, this paper introduces RegBR, the first national framework to centralize, classify and analyze regulations from the Brazilian government. A centralized database of Brazilian federal legislation built from automated ETL routines and processed with data mining and machine learning techniques was created. Our framework evaluates different NLP models in a text classification task on our novel Portuguese legal corpus and performs regulatory analysis based on metrics that concern linguistic complexity, restrictiveness, law interest, and industry-specific citation relevance. Our results were examined over time and validated by correlating them with known episodes of regulatory changes in Brazilian history, such as the implementation of new economic plans or the emergence of an energy crisis. Methods and metrics proposed by this framework can be used by policy makers to measure their own work and serve as inputs for future studies that could analyze government changes and their relationship with federal regulations.
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 | 0.007 | 0.015 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.011 | 0.006 |
| Science and technology studies | 0.002 | 0.002 |
| Scholarly communication | 0.004 | 0.004 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".