Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AI service gives Wikipedians ‘X-ray specs’ to see through bad edits

blog.wikimedia.org

Post reply on HN
Print view View original

31–40 of 52 posts

Re: AI service gives Wikipedians ‘X-ray specs’ to see through bad edits

#31

Post by jacquesm »

tptacek wrote: post #15
jacquesm wrote: post #9

Earlier quoted context omitted.

> Not really That's worrisome then. You'd expect a bit more rigor before putting a bot like that into production.

It's not actually doing reversions, right? It's just scoring edits. Wikipedia editors keep hot-lists of articles they watch edits for, or patrol lists of edits or page creations; ostensibly, all this needs to do is sort those lists of edits.

It's augmentation, not making any decisions on its own (and that's logical given the false positive rate). So it's just an aid at this point but it can probably help quite a bit with triage.

Re: AI service gives Wikipedians ‘X-ray specs’ to see through bad edits

#32

Post by halfak_wmf »

exo762 wrote: post #4

This is very peculiar. New tool is introduced, which joins a set of existing tools (bots) which address the same problem. Some comparison of quality and robustness is expected. Instead author gives us some insight into his/hers source of inspiration: > A feminist inspiration > “Please exercise extreme caution to avoid encoding racism or other biases into an AI scheme.” > Wnt (from The Signpost) And few lines below we…

+1 for Egalitarianism. So, when I use the word "feminism", I'm referring to the academic field that explores power structures in social systems. These power structures go far beyond gender issues despite what the label "feminism" implies. It's this broader sense of justice/morality in social spaces that I would like to engage with and draw inspiration from.

There are two core bits of feminist theory that I draw from as inspiration in organizing our work on this system:

* Empowerment vs. Power over -- I'm a computer scientist and I've been studying quality control in Wikipedia for 10 years. That makes me very powerful in this conversation. I could use that power to browbeat Wikipedians into changing their quality control practices to what I think we should do. But on the other hand, I don't think that my perspective is absolute. A lot of Wikipedians know better than I do how they should curate the encyclopedia. So instead, I'm trying to empower Wikipedians and our community of tool developers to imagine how they'd like quality control to work. My research[1,2,3] suggests that we need reform here and I'd rather see that reform through innovation than command and control. Honestly though, I don't need to look to feminism for this insight. I came to the same conclusion after considering Wikipedia as a complex social system[4].

* The potential for systemic biases -- As other comments have pointed out, there's inevitably systemic bias in people's behavior as they evaluate good and bad edits in Wikipedia because these judgements are inherently subjective and there's a strong incentive to push back against anything that is new and unusual -- especially, things that don't follow the western scholarly traditions of reference information. Once encoded into a black box algorithm, these biases can become even more hidden and substantially more impactful. One bias that is plainly obvious at the moment is against anonymous editors. While a lot of vandalism may come from anonymous editors, so does ~25% of productive contributions to Wikipedia articles (it's my job to measure these things). We're actively working to nerf the "is anonymous" feature and find better sources of signal.

1. Halfaker, A., Geiger, R. S., Morgan, J. T., & Riedl, J. (2012). The rise and decline of an open collaboration system: How Wikipedia’s reaction to popularity is causing its decline. American Behavioral Scientist, 0002764212469365. http://www-users.cs.umn.edu/~halfak/publications/The_Rise_an... 2. Halfaker, A., Geiger, R. S., & Terveen, L. G. (2014, April). Snuggle: Designing for efficient socialization and ideological critique. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (pp. 311-320). ACM. http://www-users.cs.umn.edu/~halfak/publications/Snuggle/hal... 3. Halfaker, A., Kittur, A., Kraut, R., & Riedl, J. (2009, October). A jury of your peers: quality, experience and ownership in Wikipedia. In Proceedings of the 5th International Symposium on Wikis and Open Collaboration (p. 15). ACM. http://www-users.cs.umn.edu/~halfak/publications/A_Jury_of_Y... 4. Halfaker, A., Kittur, A., & Riedl, J. (2011, October). Don't bite the newbies: how reverts affect the quantity and quality of Wikipedia work. In Proceedings of the 7th international symposium on wikis and open collaboration (pp. 163-172). ACM. http://www-users.cs.umn.edu/~halfak/publications/Don't_Bite_... 5. Geiger, R. S., & Halfaker, A. (2013, August). When the levee breaks: without bots, what happens to Wikipedia's quality control processes?. In Proceedings of the 9th International Symposium on Open Collaboration (p. 6). ACM. http://www-users.cs.umn.edu/~halfak/publications/When_the_Le... 6. Halfaker, A., & Riedl, J. (2012). Bots and cyborgs: Wikipedia's immune system. Computer, (3), 79-82. http://stuartgeiger.com/bots-cyborgs-halfaker.pdf

Re: AI service gives Wikipedians ‘X-ray specs’ to see through bad edits

#33

Post by halfak_wmf »

halfak_wmf wrote: post #32
exo762 wrote: post #4

This is very peculiar. New tool is introduced, which joins a set of existing tools (bots) which address the same problem. Some comparison of quality and robustness is expected. Instead author gives us some insight into his/hers source of inspiration: > A feminist inspiration > “Please exercise extreme caution to avoid encoding racism or other biases into an AI scheme.” > Wnt (from The Signpost) And few lines below we…

+1 for Egalitarianism. So, when I use the word "feminism", I'm referring to the academic field that explores power structures in social systems. These power structures go far beyond gender issues despite what the label "feminism" implies. It's this broader sense of justice/morality in social spaces that I would like to engage with and draw inspiration from. There are two core bits of feminist theory that I draw from…

Sorry about the formatting issues. I can't seem to edit the post :/

Re: AI service gives Wikipedians ‘X-ray specs’ to see through bad edits

#34

Post by halfak_wmf »

jacquesm wrote: post #30
halfak_wmf wrote: post #29

Earlier quoted context omitted.

Actually, we openly report a wide variety of statistics about our models. E.g. if you go to https://ores.wmflabs.org/scores/enwiki , the service lists out the models that are available for English Wikipedia along with test statistics. You can also browse our test statistics in our documentation. See https://meta.wikimedia.org/wiki/ORES/damaging#English_Wikipe... Currently, we're optimizing for AUC since it (1) is har…

Thank you. 75%, that's not bad but it's also not exactly 'x-ray eyes' grade yet. This is a pretty tough problem you're tackling, I can see now why it is not a bot but an augmentation device. It would be nice to track the accuracy over time, to see if the vandalizers wise up to how the bot makes the decisions to game it.

Actually our AUC is 90% and that beats the state of the art in the literature. Accuracy is easy to game. We could get 97.5% accuracy by just predicting False all of the time. We don't advise reviewers to use the prediction directly, but rather to set thresholds on the probability. 70% probability is a very conservative filter and will catch about 10% and a little bit less than half of them will actually be damaging.

So, this is useful enough to reduce the workload by 90% right now. As we increase the model's fitness, we should be able to drive that up to 95%, but I doubt we'll get much better than that.

Re: AI service gives Wikipedians ‘X-ray specs’ to see through bad edits

#35

Post by jacquesm »

halfak_wmf wrote: post #34
jacquesm wrote: post #30

Earlier quoted context omitted.

Thank you. 75%, that's not bad but it's also not exactly 'x-ray eyes' grade yet. This is a pretty tough problem you're tackling, I can see now why it is not a bot but an augmentation device. It would be nice to track the accuracy over time, to see if the vandalizers wise up to how the bot makes the decisions to game it.

Actually our AUC is 90% and that beats the state of the art in the literature. Accuracy is easy to game. We could get 97.5% accuracy by just predicting False all of the time. We don't advise reviewers to use the prediction directly, but rather to set thresholds on the probability. 70% probability is a very conservative filter and will catch about 10% and a little bit less than half of them will actually be damaging.…

> 70% probability is a very conservative filter and will catch about 10% and a little bit less than half of them will actually be damaging.

Right. This is really interesting. A while ago I wrote a classifier that predicted based on a number of criteria if a new member of a web community would be trouble or not. It also worked as an aid in classification and not as a stand-alone decision maker. You have a lot more data to work with so that should make the problem a bit more tractable.

Does it use other bits of knowledge about the edit prior probability of a revert for an edit by that particular user or network range for instance?

Re: AI service gives Wikipedians ‘X-ray specs’ to see through bad edits

#36

Post by kuschku »

zellyn wrote: post #23

Welcome to the spammer vs machine learning arms race, Wikipedia. :-) (Former YouTube Abuse team member)

Well, Wikipedia at least has humans working on it, who can catch issues and improve it.

It can’t be worse than YouTube/Google’s systems anyway.

Re: AI service gives Wikipedians ‘X-ray specs’ to see through bad edits

#37

Post by titanomachy »

kuschku wrote: post #36
zellyn wrote: post #23

Welcome to the spammer vs machine learning arms race, Wikipedia. :-) (Former YouTube Abuse team member)

Well, Wikipedia at least has humans working on it, who can catch issues and improve it. It can’t be worse than YouTube/Google’s systems anyway.

I don't see that many bot-generated comments anymore on YouTube. The genuine user-generated comments are among the lowest-quality on any site that I frequent, but I suspect there isn't much that Google can do about that.

Re: AI service gives Wikipedians ‘X-ray specs’ to see through bad edits

#38

Post by kuschku »

titanomachy wrote: post #37
kuschku wrote: post #36

Earlier quoted context omitted.

Well, Wikipedia at least has humans working on it, who can catch issues and improve it. It can’t be worse than YouTube/Google’s systems anyway.

I don't see that many bot-generated comments anymore on YouTube. The genuine user-generated comments are among the lowest-quality on any site that I frequent, but I suspect there isn't much that Google can do about that.

I’ve seen tons of spam, "buy viagra here", and I’ve seen hundreds of videos that have just an empty image, no sound, and a full-screen annotation (and a description) that link to another video site.

Re: AI service gives Wikipedians ‘X-ray specs’ to see through bad edits

#39

Post by HarryHirsch »

tptacek wrote: post #11
cowardlydragon wrote: post #10

As referenced in the article, what is "good" and "bad" is dependent on perspective. Wikipedia has several perspectives just within the colloquial / perceived mission. Is it for academic integrity? For common education? For the rich and powerful? For the everyman? To record as much as possible? To cull the best knowledge from the stream? Is it for progressive ideals, which may be opposed by the common majority? Or doe…

"Good" simply means "unlikely to be reverted". The objective is to save time for editors.

Maybe the better metric is usefulness to the reader. A suitable algorithm can recognize things like "N.N. smells", but so can any user. The current algorithms are very effective at dealing with "XY is gay" and "Buy herbal viagra"; you don't see much of that.

The really insidious stuff is spin doctors for companies and nations. So far, Wikipedia does a very poor job with geopolitical conflicts, and competing financial interests are not taken seriously enough either.

Post reply on HN