Enwiki Draft Quality Model Card[edit]

This model card was created and written entirely by the Algorithmic Accountability Bot account. The bot is operated by Hal Triedman. It regularly creates and updates pages about the provenance and statistical performance of machine learning models and datasets owned by the Wikimedia Foundation.

Note: Any and all edits to this page will be overwritten the next time it is updated. Please put all questions and discussion of this algorithmic component in the talk page, or else contact Hal or the WMF ML team directly.

This is a Tier 3 model card. That means it is generated by retrieving an in-depth explanation of the model rationale, owners, creators, provenance, etc. This can tell you who to contact to ask more questions about the model, but cannot tell you anything about model architecture, how the model performed at training time, or how the model is performing on the MediaWiki platform right now.

Qualitative Analysis[edit]

What is the motivation behind creating this model?[edit]

Assessing the quality of drafts at scale in Wikipedia is important for understanding and working to improve the quality of articles as they are being actively worked on. But this quality assessment work is time intensive for editors and never-ending (enwiki adds ~600 articles/day, on average), getting in the way of improving drafts and enabling speedy draft deletion. This model seeks to predict the quality of a draft based on its text order to support quality assessment processes.

Who created this model?[edit]

Aaron Halfaker (aaron.halfaker@gmail.com) and Amir Sarabadani (amir.sarabadani@wikimedia.de).

Who currently owns/is responsible for this model?[edit]

WMF Machine Learning Team (ml@wikimediafoundation.org)

Who are the intended users of this model?[edit]

English Wikipedia uses this model as a service for facilitating efficient reviews of draft quality. On an individual basis, anyone can submit a properly-formatted API call to ORES for a given article and get back the result of this model.

What should this model be used for?[edit]

This model should be used for facilitating draft quality predictions on English Wikipedia.

What should this model not be used for?[edit]

This model should not be used as an ultimate arbiter of the quality of a draft. That is an editorial decision and should be made by editors. It should not be used for any other English-language wiki besides English Wikipedia, and shouldn't be used for other languages.

What community approval processes has this model gone through?[edit]

English Wikipedia decided (note: don't know where/when this decision was made, would love to find a link to that discussion) to use this model. Over time, the model has been validated through use in the community. The link below is just an example to show what this product might look like.

Dates of consideration forums[edit]

2021-09-07

What internal or external changes could make this model deprecated or no longer usable?[edit]

Data drift means training data for the model is no longer usable.
Doesn't meet desired performance metrics in production.
English Wikipedia community decides to not use this model anymore.

How should this model be licensed?[edit]

Creative Commons Attribution ShareAlike 3.0

If this model is retrained, can we see how it has changed over time?[edit]

To my knowledge, this model has not been retrained over time — it still uses original training data from August 2015 - August 2016.

How does this model mitigate data drift?[edit]

This model does not mitigate data drift.

Which service(s) rely on this model?[edit]

This model is one of many models that powers ORES, the Wikimedia Foundation's machine machine learning API.

Learn more about ORES here

Which dataset(s) does this model rely on?[edit]

This model was trained using training data that seems to be from August 2015 - August 2016. More details are available in the makefile of the drafttopic github repository.