Справка:Новые фильтры для просмотра правок/Предсказание качества и намерений пользователя

From mediawiki.org
This page is a translated version of the page Help:New filters for edit review/Quality and Intent Filters and the translation is 11% complete.
Outdated translations are marked like this.
PD Примечание: Редактируя эту страницу, вы соглашаетесь на передачу своего вклада по лицензии CC0.
Подробнее — в проекте Помощь с общественным достоянием.

Новые фильтры для просмотра правок представляют две уникальных группы фильтров — "Качество вклада" и "Намерения пользователя". Они дают вероятные предсказания относительно проблемности правок и добросовестности редакторов соответственно. Небольшое знание принципов работы этих уникальных инструментов поможет вам использовать их более эффективно.

Additionally, the language-agnostic revert risk model, enabled in 2024, provides a prediction about how likely an edit is to require reverting.

Knowing a bit about how these unique tools work will help you use them more effectively.

Эти фильтры доступны только на определенных вики.

Работа на основе машинного обучения

Предсказания, на которых основаны фильтры Качества и Добросовестности, подсчитаны с помощью ORES, программы машинного обучения, натренированной на большом количестве правок, ранее сделанных людьми. Машинное обучение - мощная технология, позволяющая машинам воспроизводить некоторые ограниченные аспекты человеческого суждения.

Фильтры качества и намерений доступны только на тех вики, на которых поддерживается соответствующий модуль ORES. Качество определяется на основе модуля “вредоносности”, а намерения правок определяет модуль “добросовесности”.

Enabling ORES requires volunteers to score edits on the relevant wiki. This page explains the process and how you can get it started on your wiki.

The language-agnostic revert risk model supports all language Wikipedias and does not require manual training by volunteers.

Choosing the right tool

Looking at the Quality, Intent, and Revert Risk filters, you may notice something different about them. Unlike filters in other groups, the various options don’t target different edit properties. Instead, many of them target the same property, but offer different levels of accuracy.

Why would anyone choose to use a tool that's less accurate? Because such accuracy can come at a cost.

Increase prediction probability (higher ‘precision’)

This conceptual diagram illustrates how the Quality filters relate to one another.
This conceptual diagram illustrates how the Quality filters relate to one another on many wikis (performance varies).
As you can see, the Скорее всего проблемные filter captures results composed almost entirely of problem edits (high precision). But it captures only a small portion of all problem edits (low recall). Notice how everything in Скорее всего проблемные (and Вероятно проблемные) is also included in the broader Возможно проблемные, which provides high recall but low precision (because it returns a high percentage of problem-free edits).
You may be surprised to see that Возможно проблемные overlaps with Скорее всего хорошие. Both filters cover the indeterminate zone between problem and problem-free edits in order to catch more of their targets (broader recall).
For space reasons, the diagram doesn't accurately reflect scale.

The more “accurate” filters on the menu return a higher percentage of correct versus incorrect predictions and, consequently, fewer false positives. (In the lingo of pattern recognition, these filters have a higher “precision”.) They achieve this accuracy by being narrower, stricter. When searching, they set a higher bar for probability. The downside of this is that they return a smaller percentage of their target.

Example: The Скорее всего проблемные filter is the most accurate of the Quality filters. Performance varies from wiki to wiki, but on English Wikipedia its predictions are right more than 90% of the time. The tradeoff is that this filter finds only about 10% of all the problem edits in a given set —because it passes over problems that are harder to detect. The problems this filter finds will often include obvious vandalism.

Find more of your target (higher ‘recall’)

If your priority is finding all or most of your target, then you’ll want a broader, less accurate filter. These find more of what they’re looking for by setting the bar for probability lower. The tradeoff here is that they return more false positives. (In technical parlance, these filters have higher “recall”, defined as the percentage of the stuff you’re looking for that your query actually finds.)

Example: The Возможно проблемные filter is the broadest Quality filter. Performance varies on different wikis, but on English Wikipedia it catches about 82% of problem edits. On the downside, this filter is right only about 15% of the time.
If 15% doesn’t sound very helpful, consider that problem edits actually occur at a rate of fewer than 5 in 100—or 5%. So 15% is a 3x boost over random. And of course, patrollers don’t sample randomly; they’re skilled at using various tools and clues to increase their hit rates. Combined with those techniques, Возможно проблемные provides a significant edge.

(As noted above, ORES performs differently on different wikis, which means that some are less subject to the tradeoffs just discussed than others. On Polish Wikipedia, for example, the Вероятно проблемные filter captures 91% of problem edits, compared to 34% with the corresponding filter on English Wikipedia. Because of this, Polish Wikipedia does not need—or have—a broader Возможно проблемные filter.)

Get the best of both worlds (with highlighting)

You can get the best of both worlds by filtering broadly but highlighting using more accurate functions. Here, the user casts a wide net for damage by checking to use the broadest Quality filter, Возможно проблемные. At the same time, she identifies the worst or most obvious problems by highlighting (but not filtering with) Вероятно проблемные, Скорее всего проблемные and Вероятно недобросовестные.

The filtering system is designed to let users get around the tradeoffs described above. You can do this by filtering broadly while Highlighting the information that matters most.

To use this strategy, it’s helpful to understand that the more accurate filters, like Скорее всего проблемные, return results that are a subset of the less accurate filters, such as Возможно проблемные. In other words, all “Very likely” results are also included in the broader Возможно проблемные. (The diagram above illustrates this concept.)

Example: Find almost all damage while emphasizing the worst/most likely:
  1. With the default settings loaded,
  1. Check the broadest Quality filter, Возможно проблемные.
  1. At the same time, highlight —without checking the filter boxes— Вероятно проблемные, in yellow, and Скорее всего проблемные, in red.
Because you are using the broadest Quality filter, your results will include most problem edits (high “recall”). But by visually scanning for the yellow, red and orange (i.e., blended red + yellow) bands, you will easily be able to pick out the most likely problem edits and address them first. (Find help on using highlights without filtering.)

Find the good (and reward it)

This reviewer wants to thank new users who are making positive contributions. The Скорее всего хорошие filter isolates problem-free edits with 99% accuracy. Filtering for Новички and Учащиеся limits the search to these two experience levels, while applying a green highlight to Новички (only) enables the reviewer to distinguish at a glance between the two levels.

Good faith is easy to find, literally! So are good edits.

The Скорее всего добросовестные filter and the Скорее всего хорошие (Quality) filter give you new ways to find and encourage users who are working to improve the wikis. For example, you might use the Скорее всего хорошие filter in combination with the Новички filter to thank new users for their good work.

Example: Thank good-faith new users
  1. Clear the filters by clicking the Trashcan. Then select the Правки страницы and Человек (не бот) filters.
  2. Check the Quality filter Скорее всего хорошие.
  3. Check the User Registration and Experience filters Новички and Учащиеся (this has the hidden effect of limiting your results to registered users).
  4. Highlight the Новички filter, in green.
All edits in your results will be good edits by Newcomers (users with fewer than 10 edits and 4 days of activity) and Learners (users with fewer than 500 edits and 30 days of activity). The green highlight lets you easily distinguish between the two.

Good is everywhere!

The “good” filters mentioned above are both accurate and broad, meaning they aren’t subject to the tradeoffs described in the previous section (they combine high “precision” with high “recall”). These filters are correct about 99% of the time and find well over 90% of their targets. How can they do that?

The happy answer is that the “good” filters perform so well because good is more common than bad. That is, good edits and good faith are much, much more plentiful than their opposites—and therefore easier to find. It may surprise some patrollers to hear this, but on English Wikipedia, for example, one out of every 20 edits has problems, and only about half those problematic edits are intentional vandalism.


Filters list

On wikis where Quality and Intent Filters are deployed, some filters may be missing due to a better quality of predictions. The better ORES performs on a wiki, the fewer filter levels are needed.

Предсказание качества вклада

Скорее всего хорошие
Очень точный способ найти практически все непроблемные правки.
Возможно проблемные
Находит большинство ошибочных или вредных правок с более низкой точностью.
Вероятно проблемные
С высокой точностью находит наиболее проблемные изменения.
С средней точностью находит промежуточную часть проблемных изменений.
Скорее всего проблемные
Максимально точен в поиске очевидно ошибочных или вредных правок.

Предсказания намерений пользователя

Скорее всего добросовестные
Очень точный способ найти практически все добросовестные правки.
Возможно недобросовестные
Ищет большинство недобросовестных правок с низкой точностью.
Вероятно недобросовестные
Со средней точностью находит промежуточную часть недобросовестных изменений.

Revert risk

Filter levels TBD. Uses the Language-agnostic revert risk model.


  1. These figures come from research that went into training the “damaging” and “good faith” ORES models on English Wikipedia. That’s to say, when volunteers scored a large, randomly drawn set of test edits, this is what they found.