About this subject
Wikidata Property Value Distribution by Domain
This page measures the distribution of values for each Wikidata property, calculating skewness and identifying the most common value within items that belong to a specific domain (e.g., biology, geography, culture). The numbers are derived from the latest public Wikidata dump; each item is assigned to a domain using its instance‑of or subclass‑of statements, then property‑value pairs are counted.
Understanding these distributions highlights modelling choices and data quality issues: a highly skewed distribution may indicate over‑reliance on a single value, while a uniform spread suggests diverse usage. Such insights are rarely published because aggregating property values across Wikidata’s complex, interconnected data model requires substantial processing.
The analysis is refreshed monthly and provides downloadable CSV files for further exploration, helping editors and researchers spot gaps, biases, or opportunities for improvement in the knowledge base.