articlequality and editquality
These are ecosystem siblings, both from Wikimedia, representing distinct but related efforts to assess the quality of different types of contributions to their platforms: one for the quality of articles and the other for the quality of individual edits.
About articlequality
wikimedia/articlequality
Github mirror - our actual code is hosted with Gerrit (please see https://www.mediawiki.org/wiki/Developer_access for contributing)
This library helps Wikipedia editors automatically assess the quality of articles. You provide the text content of a Wikipedia page, and it returns a prediction of its quality class (e.g., 'stub', 'b', 'fa') along with the probabilities for each class. It's designed for Wikipedia editors or researchers who need to categorize articles efficiently.
About editquality
wikimedia/editquality
Github mirror - our actual code is hosted with Gerrit (please see https://www.mediawiki.org/wiki/Developer_access for contributing)
This library helps identify potentially problematic edits on Wikimedia projects like Wikipedia. It takes recent changes or proposed edits as input and uses machine learning models to predict their quality or likelihood of being vandalism. This helps human editors and community managers prioritize reviews and maintain content integrity.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work