User:ClueBot NG

ClueBot NG

This user is a bot
(talk · contribs)
ClueBot NG aids in Operation Enduring Encyclopedia.
Operator	Cobi (t), Crispy1989 (t) (more info)
Approved?	Yes, BRFA.
Flagged?	Yes.
Task(s)	Reverting vandalism.
Edit rate	Over 9,000 EPM.
Edit period(s)	Continually
Automatic or manual?	Automatic
Programming language(s)	C, C++, PHP, Python, Bash, and Java (more info)
Exclusion compliant?	Yes
Emergency shutoff-compliant?	Yes
Other information	ClueBot NG is run from the ClueNet servers and Wikimedia Labs infrastructure.

Documentation

Administrator emergency shutoff

Administrators may turn the bot off by changing this page to 'False'.

Exclusion compliant

This bot is an exclusion compliant bot.

Summary

ClueBot NG is an anti-vandal bot that tries to detect and revert vandalism quickly and automatically.

Team

• Christopher Breneman — Crispy1989 (talk · contribs) — wrote and maintains the core detection engine and core configuration.
• Cobi Carter — Cobi (talk · contribs) — wrote and maintains the Wikipedia interface code and review interface.

Special thanks to:

• Tim — Tim1357 (talk · contribs) — For writing the original dataset downloader code and providing the original dataset.
• Methecooldude (talk · contribs) — For providing server resources at ClueNet.
• DamianZaremba (talk · contribs), SnoFox (talk · contribs), H3llkn0wz (talk · contribs) & b930913 (talk · contribs) — For helping with minor issues, testing, and people-handling.
• Every user who has contributed to the dataset review interface.
• Everyone who has made a helpful and useful suggestion.

Questions, comments, contributions, and suggestions regarding:

• the core engine, algorithms, and configuration should be directed to Crispy1989 (talk · contribs).
• the bot's interface to Wikipedia and dataset review interface should be directed to Cobi (talk · contribs).
• the bot's original dataset should be directed to Tim1357 (talk · contribs).

IRC Channel

ClueBot NG's development and discussion about internals takes place almost entirely on its IRC channel. The IRC channel can be accessed on irc.cluenet.org channel #cluebotng. Please join if you have any detailed questions about the internals or would like to speak real-time with the developers.

Bots in #cluebotng that may be useful are:

• CBNG-RC — RCBot for the report interface. Relays new reports, report comments and changes in status (such as reports getting picked up by the review interface).
• ClueBot_NG — Live bot, mostly does nothing but relays some edit info such as pages listed on User:Cobi/CBAutoedit.js

Dataset Review Interface

For the bot to be effective, the dataset needs to be expanded. Our current dataset has some degree of bias, as well as some inaccuracies. We need volunteers to help review edits and classify them as either vandalism or constructive. We hope to eventually completely replace our current dataset with a random sampling of edits, reviewed and classified by volunteers. More thorough instructions on how to use the interface, and the interface itself, are at the dataset review interface (currently broken).

Extended statistics on contributors, including edit review counts and accuracy, are available here.

For those that help with and contribute to the review interface, a user box is available for you:

	This user reviews dataset edits for ClueBot NG to help automatically mass revert vandalism on Wikipedia.

Use it with: {{User:ClueBot NG/Review User Box}}

Statistics

As ClueBot-NG requires a dataset to function, the dataset can also be used to give fairly accurate statistics on its accuracy and operation. Different parts of the dataset are used for training and trialing, so these statistics are not biased.

The exact statistics change and improve frequently as we update the bot. Currently:

• Selecting a threshold to optimize total accuracy, the bot correctly classifies over 90% of edits.
• Selecting a threshold to hold false positives at a maximal rate of 0.1% (current setting), the bot catches approximately 40% of all vandalism.
• Selecting a false positive rate of 0.25% (old setting), the bot catches approximately 55% of all vandalism.

Currently, the trial dataset used to generate these statistics is a random sampling of edits, each reviewed by at least two humans, so statistics are accurate.

Note: These statistics are calculated before post-processing filters. Post-processing filters primarily reduce false positive rate (ie, the actual number of false positives will be less than stated here), but can also slightly reduce catch rate.

Frequently Asked Questions

See the FAQ.

Vandalism Detection Algorithm

ClueBot-NG uses a completely different method for classifying vandalism than all previous anti-vandal bots, including the original ClueBot. Previous anti-vandal bots have used a list of simple heuristics and blacklisted words to determine if an edit is vandalism. If a certain number of heuristics matched, the edit was classified as vandalism. This method results in quite a few false positives, because many of the heuristics have legitimate uses in some contexts, and only about a 5% to 10% vandalism catch rate, because most vandalism cannot be detected by these simple heuristics.

ClueBot-NG uses a combination of different detection methods which use machine learning at their core. These are described below.

Machine Learning Basics

Instead of a predefined list of rules that a human generates, ClueBot-NG learns what is considered vandalism automatically by examining a large list of edits which are preclassified as either constructive or vandalism. Its concept of what is considered vandalism is learned from human vandal-fighters. This list of edits is called a corpus or dataset. The accuracy of the bot largely depends on the size and quality of the dataset. If the dataset is small, contains inaccurately classified edits, or does not contain a random sampling of edits, the bot's performance is severely hampered. The best thing you and other Wikipedians can do to help the bot is to improve the dataset. If you're interested in helping out, please see the Dataset Review Interface section.

Bayesian Classifiers

A few different Bayesian classifiers are used in ClueBot-NG. The most basic one works in units of words. Essentially, for each word, the number of constructive edits that add the word, and the number of vandalism edits that add the word, are counted. This is used to form a vandalism-probability for each added word in an edit. The probabilities are combined in such a way that not only words common in vandalism are used, but also words that are uncommon in vandalism can reduce the score.

This differs from a simple list of blacklisted words in that word weights are exactly determined to be optimal, and there's also a large "whitelist" of words, also with optimal weights, that contributes.

Currently, there's also a separate Bayesian classifier that works in units of 2-word phrases. We may add even more Bayesian classifiers in the future that work in different units of words, or words in different contexts.

Scores from the Bayesian classifiers alone are not used. Instead, they're fed into the neural network as simple inputs. This allows the neural network to reduce false positives due to simple blacklisted words, and to catch vandalism that adds unknown words.

Artificial Neural Network

The main component of the ClueBot-NG vandalism detection algorithm is the neural network. An artificial neural network is a machine learning technique that can recognize patterns in a set of input data that are more complex than simply determining weights. The input to the ANN used in ClueBot-NG is composed of a number of different statistics calculated from the edit, which include, among many other things, the results from the Bayesian classifiers. Each statistic has to be scaled to a number between zero and one before being input to the neural network.

The output of the neural network is used as the main vandalism score for ClueBot-NG. As with other machine-learning techniques, the score's accuracy depends on the training dataset size and accuracy.

Threshold Calculation

The ANN generates a vandalism score between 0 and 1, where 1 is 100% sure vandalism. To classify some edits as vandalism, and some as constructive, a threshold must be applied to the score. Scores above the threshold are classified as vandalism, and scores below the threshold are classified as constructive.

The threshold is not randomly chosen by a human, but is instead calculated to match a given false positive rate. When doing actual vandalism detection, it's important to minimize false positives to a very low level. A human selects a false positive rate, which is the percentage of constructive edits incorrectly classified as vandalism. A threshold is calculated to have a false positive rate at or below this percentage, while maximizing catch rate. False positive rate is set by a human, and the bot stays at or below that false positive rate, while catching as much vandalism as possible. The false positive rate is not fixed, but is adjustable.

To make sure the threshold and statistics are accurate and do not give inaccurate statistics or a higher false positive rate than expected, the portion of the dataset used for threshold calculations is kept separate from the training set, and is not used for training. Also, only the most accurate parts of the dataset (currently, the ones that are human-reviewed from the review interface) are used for this calculation. This ensures that all statistics given here are accurate, and that false positives will not exceed the given rate.

Post-Processing Filters

After the core makes its primary vandalism determination, the data is given to the Wikipedia interface. The Wikipedia interface contains some simple logic designed to reduce false positives. Although it also reduces vandalism catch rate a small amount, it also reduces false positive rate, and some of these are mandated by Wikipedia policy.

The first two of these rarely reduce catch rate, but both prevent a fair number of false positives. Note: The false positive rate (and catch rate) are calculated in the core, before post-processing filters. This means that actual false positive rate will be less than stated false positive, often by a significant factor.

• User Whitelist — If an edit made by a user that is in a whitelist is classified as vandalism, the edit is not reverted.
• Edit Count — If a user has more than a threshold number of edits, and fewer than a threshold percentage of warnings, the edit is not reverted.
• 1RR — The same user/page combination is not reverted more than once per day, unless the page is on the angry revert list.

Development News/Status

Core Engine

• Current version is working well.
• Currently writing a dedicated wiki markup parser for more accurate markup-context-specific metrics. (No existing alternative parsers are complete or fast enough)

Dataset Review Interface

• Code to import edits into database is finished.
• Currently changing logic that determines the end result for an edit.

Dataset Status

• We found that the Python dataset downloader we used to generate the training dataset does not generate data that is identical to the live downloader. It's possible that this is greatly reducing the effectiveness of the live bot. We're working on writing shared code for live downloading and dataset generation so we can regenerate the dataset.
• This has been fixed and the bot retrained. It's now working much better.
• Currently getting more data from the review interface.

Languages

• C / C++ — The core is written in C/C++ from scratch.
• PHP — The bot shell (Wikipedia interface) is written in PHP, and shares some code with the original ClueBot.
• Java — The dataset review interface is written in Java using the Google App framework.
• Bash — A few scripts to make it easier to train and maintain the bot are Bash scripts.
• Python — Some of the original dataset management and downloader tools were written in Python.

Source Code

The source code for the bot is public, and can be found on github. Please join the IRC channel and ask the devs for access. If you would like to run the bot for yourself on your own wiki, you should discuss with the devs all the factors involved in making it work properly. You should also be aware that it will only run on a Linux/UNIX system, and the source code can be rather difficult to compile (many dependencies) unless you're experienced with Linux/UNIX systems.

ClueBot-NG RC Feeds

ClueBot-NG provides two IRC-based feeds of its data, primary intended for use by other automated tools. Both feeds are on the server irc.cluenet.org. The feeds are:

• Vandalism Feed on #wikipedia-van — This is a feed of all edits that ClueBot-NG calculates to be above vandalism threshold. Not all of these edits are reverted due to post-processing filters. The edit's score, whether it was or was not reverted, and the reason for the revert/not-revert, is given in the feed. Format is \x0315[[\x0307 article title \x0315]] by "\x0303 edit user \x0315" (\x0312 diff url \x0315) \x0306 Revert time (in seconds) \x0315 ("\x0304 Reverted or Not Reverted \x0315) (\x0313 Reason \x0315) (\x0302 Process time (in seconds) \x0315s).
• Complete RC Feed on #cluebotng-spam — This is essentially a copy of the Wikipedia RC feed, but with ClueBot-NG's analysis data added. It includes everything the Wikipedia RC feed does, with the addition of the ClueBot-NG score and whether it was reverted or not. Format is edit line \003 # score # reason # Reverted or Not reverted

Note that edits in the feed may not necessarily be in precise order, because ClueBot-NG processes them in parallel. But non-reverted edits are usually processed in under a second. Reverted edits can sometimes take up to 10 seconds or more to process due to API lag on reverting.

Information About False Positives

ClueBot-NG is not a person, it is an automatic robot that tries to detect vandalism and keep Wikipedia clean. A false positive is when an edit that is not vandalism is incorrectly classified as vandalism.

The bot is not biased against you, your edit, or your viewpoint (unless your edit is vandalism). False positives are rare, but do occur. By handling false positives well without getting upset, you are helping this bot catch almost half of all vandalism on Wikipedia and keep the wiki clean for all of us.

False positives with ClueBot-NG are (essentially) inevitable. For it to be effective at catching a great deal of vandalism, a few constructive (or at least, well-intentioned) edits are caught. There are very few false positives, but they do happen. If one of your edits is incorrectly identified as vandalism, simply redo your edit, remove the warning from your talk page, and if you wish, report the false positive. ClueBot-NG is not (yet) sentient — it is an automated robot, and if it incorrectly reverts your edit, it does not mean that your edit is bad, or even substandard — it's just a random error in the bot's classification, just like email spam filters sometimes incorrectly classify messages as spam.

The reason false positives are necessary is due to how the bot works. It uses a complex internal algorithm called an Artificial Neural Network that generates a probability that a given edit is vandalism. The probability is usually pretty close, but can sometimes be significantly different from what it should be. Whether or not an edit is classified as vandalism is determined by applying a threshold to this probability. The higher the threshold, the fewer false positives, but also less vandalism is caught. A threshold is selected by assuming a fixed false positive rate (percentage of constructive edits incorrectly classified as vandalism) and optimizing the amount of vandalism caught based on that. This means that there will always be some false positives, and it will always be at around the same percentage of constructive edits. The current setting of the false positive rate is listed in Statistics above.

When false positives occur, they may not be poor quality edits, and there may not even be an apparent reason. If you report the false positive, the bot maintainers will examine it, try to determine why the error occurred, and if possible, improve the bot's accuracy for future similar edits. While it will not prevent false positives, it may help to reduce the number of good-quality edits that are false positives. Also, if the bot's accuracy improves so much that the false positive rate can be reduced without a significant drop in vandalism catch rate, we may be able to reduce the overall number of false positives.

If you want to help significantly improve the bot's accuracy, you can make a difference by contributing to the review interface. This should help us more accurately determine a threshold, catch more vandalism, and eventually, reduce false positives.

To report a false positive, or to see a full list of all false positives, see here.

User box

For those that help with and contribute to the false positive interface, a user box is available for you:

	This user reviews false positive reports for ClueBot NG to help revert vandalism on Wikipedia.

Use it with:

{{User:ClueBot NG/Report User Box}}

Awards

Show all awards

		The Anti-Vandalism Barnstar
		Regardless of that below 0.005% of your edits are false-positives, you make us all proud for saving Wikipedia otherwise. Good job! Gamingforfun365 (talk) 01:27, 27 March 2016 (UTC)

	The Anti-Vandalism Barnstar
	You're on 24/7 and are awesome Krett12 (talk) 21:48, 28 January 2016 (UTC)

	Infinite Skill award
	ClueBot NG is excelente. Without you, we'd have so much vandalism... and you're efficient too! [ EnigmaLord515 (talk) 20:40, 24 January 2016 (UTC) ]

	Bot award
	You make our lives easier, with your diligent robot beeps and boops. Regards, CoconutPaste (talk) 03:04, 21 January 2016 (UTC)

	The Random Acts of Kindness Barnstar
	Don't ever stop Cluebot! JJ Davis 01:30, 10 January 2016 (UTC)

amazing Eyestone40000 (talk) 18:02, 5 January 2016 (UTC)

		The Anti-Vandalism Barnstar
		You are the greatest vandal enforcer of all time. I salute you. SupremeRulerGFG (talk) 22:44, 22 December 2015 (UTC)

Thanks for reverting vandalism so quickly, ClueBot NG! You do so much to make Wikipedia better!

Michael Barera (talk) 02:16, 25 November 2015 (UTC)

	The Tireless Contributor Barnstar
	I reward you this barnstar for being tireless contributers, and always reverting Wikipedia, and keeping articles safe! Keep up the good work :) - Minionlover2015 (talk) 22:27, 21 November 2015 (UTC)

	The Anti-Vandalism Barnstar
	Thank you based cluebot for catching those nasty vandals. Weegeerunner chat it up 16:56, 5 November 2015 (UTC)

Praise

Show all praise

Happy New Year ClueBot Commons!

Happy New Year!

ClueBot Commons,
Have a prosperous, productive and enjoyable New Year, and thanks for your contributions to Wikipedia. Poepkop (talk) 17:53, 31 December 2015 (UTC)

Send New Year cheer by adding {{subst:Happy New Year 2016}} to user talk pages.

.

I am impressed with how well this bot operates. My only complaint is that it sometimes beats me to vandalism reverts! I suppose that is a good thing though. Merry Christmas, Cluebot NG!

Chesnaught555 (talk) 19:15, 24 December 2015 (UTC)

Absolutely fabulastic antivandalist, must be the most productive one there is working 24/7, and best of all, you just keep on working over Christmas and New Year without complaining! Merry Christmas and Happy New Year, Cluebot! Poepkop (talk) 11:27, 24 December 2015 (UTC)

Youre awesome ClueBotNG! Of course I get really angry when I go to a diff from recent changes to find you've already reverted it. But still, I have beaten you to a lot of vandalism lately, so I guess I shouldn't complain. (-; BlAcKhAt9(9 (talk) 22:17, 30 November 2015 (UTC)

Apparently people are going crazy-loco-nutso about them beating this bot to vandalism, and I didn't know about this thing until now. I just wanted to stop by and say that I beat this bot here to some vandalism on the Psilocybin mushroom Wikipedia page. Nana-nana-boo-boo! :D tgtw 03:11, 3 June 2015 (UTC)

You are BOSS!!!!!!!! — Preceding unsigned comment added by 172.2.57.181 (talk) 11:59, 18 October 2015‎

Contributions

My Contributions