Slashdot Mirror
Crowdsourcing the Censors: A Contest
Before you get bored and click away: I'm proposing an algorithm for Facebook (and similar sites) to use to review "abuse reports" in a scalable and efficient manner, and I'm offering a total of $100 (or more) to the reader (or to some charity designated by them) who proposes the best improvement(s) or alternative(s) to the algorithm. We now proceed with your standard boilerplate introductory paragraph.
In his new book The Net Delusion: The Dark Side of Internet Freedom, Evgeny Morozov cites examples of Facebook users organizing campaigns to shut down particular groups or user account by filing phony complaints against them. One Hong-Kong-based Facebook group with over 80,000 members, formed to oppose the pro-Beijing Democratic Alliance for the Betterment and Progress of Hong-Kong, was shut down by opponents flagging the group as "abusive" on Facebook. In another incident, the Moroccan activist Kacem El Ghazzali found his Facebook group Youth for the Separation between Religion and Education deleted without explanation, and when he e-mailed Facebook to ask why, his personal Facebook profile got canned as well. Only after an international outcry did Facebook restore the group (but, oddly, not El Ghazzali's personal Facebook account), but they refused to explain the original removal; the most likely cause was a torrent of phony "complaints" from opponents. In both cases it seemed clear that the groups did not actually violate Facebook's Terms of Service, but the number of complaints presumably convinced either a software algorithm or an overworked human reviewer that something must have been inappropriate, and the forums were shut down. The Net Delusion also describes a group of conservative Saudi citizens calling themselves "Saudi Flagger" that coordinates filing en masse complaints against YouTube videos which criticize Islam or the Saudi royal family.
A large number of abuse reports against a single Facebook group or YouTube video probably has a good chance of triggering a takedown; with 2,000 employees managing 500 million users, Facebook surely doesn't have time to review every abuse report properly. About once a month I still get an email from Facebook with the subject "Facebook Warning" saying:
You have been sending harassing messages to other users. This is a violation of Facebook's Terms of Use. Among other things, messages that are hateful, threatening, or obscene are not allowed. Continued misuse of Facebook's features could result in your account being disabled.
I still have no idea what is triggering the "warnings"; the meanest thing I usually say on Facebook is to people who write to me asking for tech support (usually with the proxy sites to get on Facebook at school), when they say "It gives me an error", and I write back, "TELL ME THE ACTUAL ERROR MESSAGE THAT IT GIVES YOU!!" (Typical reply: "It gave me an error that it can't do it." If you work in tech support, I feel your pain.) I suspect the "abuse reports" are probably coming from parents who hack into their teenagers' accounts, see their teens corresponding with me about how to get on Facebook or YouTube at school, and decide to file an "abuse report" against my account just for the hell of it. If Facebook makes it that easy for a lone gunman to cause trouble with fake complaints, imagine how much trouble you can make with a well-coordinated mob.
But I think an algorithm could be implemented that would enable users to police for genuinely abusive content, without allowing hordes of vigilantes to get content removed that they simply don't like. Taking Facebook as an example, a simple change in the crowdsourcing algorithm could solve the whole problem: use the votes of users who are randomly selected by Facebook, rather than users who self-select by filing the abuse reports. This is similar to an algorithm I'd suggested for stopping vigilante campaigns from "burying" legitimate content on Digg (and indeed, stopping illegitimate self-promotion on Digg at the same time), and as an general algorithm for preventing good ideas from being lost in the glut of competing online content. But if phone "abuse reports" are also being used to squelch free speech in countries like China and Saudi Arabia, then the moral case for solving the problem is all that more compelling.
Here's how the algorithm would work: Facebook can ask some random fraction of their users, "Would you like to be a volunteer reviewer of abuse reports?" (Would you sign up? Come on. Wouldn't you be a little bit curious what sort of interesting stuff would be brought to your attention?) Wait until they've built up a roster of reviewers (say, 20,000). Then suppose Facebook receives an abuse report (or several abuse reports, whatever their threshold is) about a particular Facebook group. Facebook can then randomly select some subset of its volunteer reviewers, say, 100 of them. This is tiny as a proportion of the total number of reviewers (with a "jury" size of 100 and a "jury pool" of 20,000, a given reviewer has only a 1 in 200 chance of being called for "jury duty" for any particular complaint), but still large enough that the results are statistically significant. Tell them, "This is the content that users have been complaining about, and here is the reason that they say it violates our terms of service. Are these legitimate complaints, or not?" If the number of "Yes" votes exceeds some threshold, then the group gets shuttered.
It's much harder to cheat in this system, than in an "abuse report" system in which users simply band together and file phony abuse reports against a group until it gets taken down. If the 200 members of "Saudi Flagger" signed up as volunteer reviewers, then they would comprise only 1% of a jury pool of 20,000 users, and on average would only get one vote on a jury of 100. You'd have to organize such a large mob that your numbers would comprise a significant portion of the 20,000 volunteer reviewers, so that you would have a significant voting bloc in a given jury pool. (And my guess is that Facebook would have a lot more than 20,000 curious volunteers signed up as reviewers.) On the other hand, if someone creates a group with actual hateful content or built around a campaign of illegal harrassment, and the abuse reports start coming in until a jury vote is triggered, then a randomly selected jury of reviewers would probably cast enough "Yes" votes to validate the abuse reports.
Jurors could in fact be given three voting choices:
- "This group really is abusive" (i.e. the abuse reports were legitimate), or;
- "This group does not technically violate the Terms of Service, but the users who filed abuse reports were probably making an honest mistake" (perhaps a common choice for groups that support controversial causes, or that publish information about semi-private individuals); or
- "This group does not violate the TOS, and the abuse reports were bogus to begin with" (i.e. almost no reasonable person could have believed that the group really did violate the TOS, and the abuse reports were probably part of an organized campaign to get the group removed).
This strongly discourages users from organizing mob efforts against legitimate groups; if most of the jury ends up voting for the third choice, "This is an obviously legitimate group and the complaints were just an organized vigilante campaign", then the users who filed the complaints could have their own accounts penalized.
What I like about this algorithm is that the sizes and thresholds can be tweaked according to what you discover about the habits of the Facebook content reviewers. Suppose most volunteer reviewers turn out to be deadbeats who don't respond to "jury duty" when they're actually called upon to vote in an abuse report case. Fine — just increase the size of the jury, until the average number of users in a randomly convened jury who do respond, is large enough to be statistically significant. Or, suppose it turns out that people who sign up to review content to be deleted, are a more prudish bunch than average, and their votes tend to skew towards "delete it now!" in a way that is not representative of the general Facebook community. Fine — just raise the threshold for the percentage of "Yes" votes required to get content deleted. All that's required for the algorithm to work, is that content which clearly does violate the Terms of Service, gets more "Yes" votes on average than content that doesn't. Then make the jury size large enough that the voting results are statistically significant, so you can tell which side of the threshold you're on.
Another beneficial feature of the algorithm is that it's scaleable — there's no bottleneck of overworked reviewers at Facebook headquarters who have to review every decision. (They should probably review a random subset of the decisions to make sure the "juries" are getting what seems to be the right answer, but they don't have to check every one.) If Facebook doubles in size — and the amount of "abusive content" and the number of abuse reports doubles along with it — then as long as the pool of volunteers reviewers also doubles, each reviewer has no greater workload than they had before. But the workload of the abuse department at Facebook doesn't double.
Now, this algorithm ducks the question of how to handle "borderline" content. If a student creates a Facebook group called "MR. LANGAN IS A BUTT BRAIN," is that "harassment" or not? I would say no, but I'm not confident that a randomly selected pool of reviewers would agree. However, the point of this algorithm is to make sure that if content is posted on Facebook that almost nobody would reasonably agree is a violation of their Terms of Service, then a group of vigilantes can't get it removed by filing a torrent of abuse reports.
Also, this proposal can't do much about Facebook's Terms of Service being prudish to begin with. A Frenchman recently had his account suspended because he used a 19th-century oil painting of an artistic nude as his profile picture. Well, Facebook's TOS prohibits nudity -- not just sexual nudity, but all nudity, period. Even under my proposed algorithm, jurors would presumably have to be honest and vote that the painting did in fact violate Facebook's TOS, unless or until Facebook changes the rules. (For that matter, maybe this wasn't a case of prudishness anyway. I mean, we know it's "artistic" because it's more than 100 years old and it was painted in oils, right? Yeah, well check out the painting that the guy used as his profile picture. It presumably didn't help that the painting is so good that the Facebook censors probably thought it was a photograph.)
But notwithstanding these problems, this algorithm was the best trade-off I could come up with in terms of scalability and fairness. So here's the contest: Send me your best alternative, or best suggested improvement, or best fatal flaw in this proposal (even if you don't come up with something better, the discovery of a fatal flaw is still valuable) for a chance to win (a portion of) the $100 -- or, you can designate a charity to be the recipient of your winnings. Send your ideas to bennett at peacefire dot org and put "reporting" in the subject line. I reserve the right to split the prize between multiple winners, or to pay out more than the original $100 (or give winners the right to designate charitable donations totalling more than $100) if enough good points come in (or to pay out less than $100 if there's a real dearth of valid points, but there are enough brainiacs reading this that I think that's unlikely). In order for the contest not to detract from the discussion taking place in the comment threads, if more than one reader submits essentially the same idea, I'll give the credit to the first submitter -- so as you're sending me your idea, you can feel free to share it in the comment threads as well without worrying about someone re-submitting it and stealing a portion of your winnings. (If your submission is, "Bennett, your articles would be much shorter if you just state your conclusion, instead of also including a supporting argument and addressing possible objections", feel free to submit that just in the comment threads.)
In The Net Delusion, Morozov concludes his section on phony abuse reports by saying, "Good judgment, as it turns out, cannot be crowdsourced, if only because special interests always steer the process to suit their own objectives." I think he's right about the problems, but I disagree that they're unsolvable. I think my algorithm does in fact prevent "special interests" from "steering the process", but I'll pay to be convinced that I'm wrong. Today I'm just choosing the "winners" of the contest myself; maybe someday I'll crowdsource the decision by letting a randomly selected subset of users vote on the merits of each proposal... but I'm sure some of you are dying to tell me why that's a bad idea.
Don't rely on the cooperation of self-serving and outwardly evil companies to send your message.
I'll take my prize in zorkmids, thanks.
So he's crowd-sourcing the crowd-sourcing solution. One more level and we'll make a black hole!
This sounds a lot like the slashdot moderation scheme...
For those who did not know, you can get the source code behind slashdot here
I'd be more likely to deputize to people who you find are more reliable (basically, trusted moderators chosen from your randomly-selected pool after reviewing their decisions). Your system assumes that most people will be reasonable. I think that is an inherently flawed assumption, including for the very situations listed above. You can't trust that only a minority will think you should remove something that is against the mainstream view.
The painting mentioned as a profile picture is Courbet's Origin of the World.
Probably best not check it out at work.
Although, of course, it is on the wall of a major gallery where anyone can see it.
Sigs are so 1990s. No way would I be seen dead with one.
..but I have to say it's ironic that you're posting about this algorithm on Slashdot, a site whose moderation system has incorporated the best of your ideas for years, and yet that doesn't seem to come up when you're asking for ideas.
I like the Slashdot system. Moderators are assigned points at times beyond their control, to prevent just the kind of abuses you mention. There's appropriate feedback control on how moderators behave. The job of moderating (and meta-moderating) is presented and appreciated in such a way that people actually do it. People are picked to do moderation in a reasonable way. The process is transparent, and the proof that it works is that the Slashdot comments you typically see are actually not horrible (usually) and sometimes are quite informative.
Let's not stir that bag of worms...
I have two algorithms, and I suggest that they are more valuable if used together, and indeed, if all three including your algorithm are used together.
(1) Identify "clumps" of users by who their friends are and by their viewing habits. Facebook has an app that will create a "distance graph," using a published algorithm. It is established that groups of users tend to "clump" and the clumps can be identified algorithmically. For example, for a given user, are there more connections back to the clump than there are to outside the clump? Another way to determine such a clump is by counting the number of loops back to the user. (A friends B friends C friends A.) Traditional correlation can be used to match viewing habits. This is probably improved by including a time factor in the each correlation term. For example, if two users watch the same video within 24 hours of each other this correlation term has more weight than if they were watched a week apart.
Now that you have identified a clump -- which you do not make public -- determine what fraction of the abuse reports come from one or a small number of clumps. That is very suspicious. Also apply an "complaint" factor to the clump as a whole. Clumps with high complaint factors (complain frequently) have their complaints de-weighted appropriately. Rather than "on-off" determinations (e.g. "banned"), use variable weightings.
In this way groups of like-minded users who try to push a specific agenda through abuse complaints would find their activities less and less effective. The more aggressive the clump, the less effective. And, the more the clump acts like a clump, the less effective.
(2) Use Wikipedia style "locking." There are a sequence of locks, from mild to extreme. Mild locks require complaining users to be in good standing and be a user for while for the complaint to count. Medium locks require a more detailed look, say, by your set of random reviewers. Extreme locks means that the item in question has been formally reviewed and the issue is closed. In addition, complaints filed against a locked ("valid") item hurt the credibility score of the complainer.
I hope this helps.
I will create a sig when innovation restarts in the U.S.
Actually, you can use moderation (and a bit of graph theory) to do just that. At first, you shouldn't put stock in any user. But, when you have a large group who usually agree, and (here's the key point) usually agree with the professional moderators, you should trust that large group. This can easily be reduced to an eigenvalue problem, similar to PageRank.
The problem I see with this idea as a whole is teens posting naked pictures of themselves and others. Then, this moderation scheme turns into a portal for child porn. Whether or not you think teens should have the right to take and distribute naked pictures of themselves, setting up a website to intentionally distribute such material is illegal.
I like the idea, however your problem is you will always come across trolls on the internet, or people who just like screwing up systems. I would say this percentage on facebook is quite sizable, so i would propose these alterations(to be taken individually or all together or mix/match):
Assign a trustability value to each juror, that is hidden and modified in one of two ways(or both):
Have a pool of pre-existing cases(I'm sure facebook has tons of examples stored in their history banks).
In this situation facebook knows what the outcome should be according to their standards.
Have any prospective juror have a mix of "real" cases and these pre-existing cases mixed together for a trial period, say that first 20 cases they review have an unknown mix. This way they can't guess which ones are appropriate or not.
Use their verdicts on these existing cases to assign a juror a "reliability" factor on their verdicts on the non-example cases in their batch.
That way jurors who don't quite get the rules, or are causing problems, are easily weeded out and their vote counts less in the total verdict weight on their real cases.
Alternatively:
Trustability starts at 50%, so new jurors get half votes.
whenever a juror disagrees with the majority opinion by the polar opposite choice, lower their trustability rating.
Likewise when they are in the majority and it is not a middleground, increase their trustability.
Both of these improvements will lower the odds of troll or mob mentality, even if the control a decent size of the juror pool because their individual votes will be worth less, while being invisible enough to the end-user that they won't be able to tell they aren't being effective.
You never realize how much manually made unmanaged "linked" lists suck, till you have src.link.link.link.link...
Although you can't expect people to identify themselves as being knowledgeable about every conflict, argument, religious view, political wrangling or moral panic you could choose individuals from the same timezone and hemisphere that the complaints originate from (and maybe only ban the offending piece in that geography - unless more complaints are received from outside).
politicians are like babies' nappies: they should both be changed regularly and for the same reasons
I think you'd be hard-pressed to find a group of people who would familiarize themselves with the Facebook TOS well enough to actually enforce it. I'm afraid that what you'd actually get is a group of people who vote Offensive/Inoffensive based on whether they agree with whatever controversial topic is at hand. This puts any minority group (LGBT, religious organizations, etc.), as well as any controversial groups (pro-Life/pro-Choice, political groups, etc.) at a much higher risk than they are now. You need some sort of incentive for people to vote according to the rules, rather than voting for what they think is right.
This is a well-studied "Who watches the watchers?" web of trust type issue. While there is no perfect solution, there are a number of good approaches. This page on Advgato describes a good trust metric for reducing the impact of spam and malicious attacks. It wouldn't be that big of a deal for FaceBook to incorporate some such system. However, it would require FaceBook to actually care about about being fair to its users, which it doesn't. FaceBook exploits for financial gain the tribal desires of people to band together and be part of a group. So FaceBook's really uses its abuse policy as a way to force people to follow the rules of the bigger and more aggressive tribes. Such battles actually help FaceBook to be successful because it strengthens the tribal behaviors that benefit FaceBook's bottom line.
So all in all, no matter what brilliant, cost-effective, robust moderation/abuse system you design or crowd source, the very, very best that you can hope for is that somebody at FaceBook might pat you on the head and thank you for your efforts and say that they aren't interested in your contribution at this time.
Why not "test" the jurors every so often to determine if they're really effective jurors?
It would work something like this: you would have a small group (employees of facebook, or wherever) that takes (actual) select complains and determine how their "ideal" juror would handle the complaint. feed these at random to the jury pool and if they're not voting the way they should, reduce (or remove) their voting power in effecting the outcome in the decision making process, alternatively if they have a strong history of voting exactly the way they should then their votes would carry more weight in non-test cases.
I wouldn't necessarily "kick out" jurors, but their voting power could be diminished to nothing if they have a very poor track record... I also don't think that the jurors should know that they're being tested nor, what their voting power is, nor that their voting power even has more or less weight than anyone else's.
Collector's Edition