Annotated chemical policies from the BURL (Italy)

The dataset contains annotated policy documents related to air-related chemical regulation extracted from the BURL (Bollettino Ufficiale Regionale Lombardia). The main objective is to identify chemical policies in the BURL and provide them in a usable and interoperable tabular format for epidemiological and environmental health research.

Weekly BURL publications were processed to extract individual policy texts and enrich them with structured metadata and semantic annotations. Automated text analysis was used to identify references to chemical substances and atmospheric contexts, focusing on air-related chemicals monitored by Agenzia Regionale per la Protezione dell'Ambiente (ARPA) della Lombardia. Only policies containing both chemical terms and atmosphere-related references within the same document were retained. All texts and annotations are in Italian, reflecting the original language of the source documents.

The dataset includes the following categories of information:

Publication and temporal metadata, such as the bulletin date, bulletin identifier and type, reference year and week of the BURL, and derived weekly and monthly publication dates (ISO standard).

Document provenance and file-level metadata, including references to the original PDF source, file name, and total word count.

Chemical and environmental annotations, capturing the presence and frequency of references to chemical substances and related regulatory themes. These include matched chemical entities, counts of identified chemicals, and thematic indicators related to air quality actions, chemical transport, toxic pollution, environmental agencies (e.g. ARPA), and provincial references.

Policy identification metadata, including policy titles and unique policy identifiers, enabling traceability and linkage with external policy databases or legal archives.

This is a preliminary release (version 0.1.0) and currently includes air-related chemical policies only. Future versions will extend the dataset to include water-related chemicals and additional environmental domains.

The dataset is intended for reuse in policy analysis, environmental epidemiology, and computational research on chemical regulation.