Objective Revision Evaluation Service: Difference between revisions

Revision as of 07:18, 14 August 2016

Revision as of 19:14, 16 August 2016

Line 32:

One of the most critical concerns about Wikimedia's open projects is the review of potentially damaging contributions. There's also the need to identify good-faith contributors (who may be inadvertently causing damage) and offering them support. These models intended to make the work of filtering through the recentchanges feed easier. [[#ORES edit quality flow]] shows how the stream of edits can be labeled as "good", "needs review" and "damaging" by the machine learning models.

*<code>[[ORES/damaging|damaging]]</code> -- predicts whether or not an edit causes damage. The morehigher scorethe means"true" it'sprobability, the more likely tothe edit bewas damaging.

*<code>[[ORES/goodfaith|goodfaith]]</code> -- predicts whether an edit was saved in good-faith. The morehigher scorethe means"true" it'sprobability, the more likely tothe edit bewas donesaved in good faith.

*<code>[[ORES/reverted|reverted]]</code> -- predicts whether an edit will eventually be reverted. The morehigher scorethe means"true" it'sprobability, the more likely tothe edit will be reverted.

<br style="clear: right;" />