Facebook blames Scoble snafu on spam false positive

Facebook blames Scoble snafu on spam false positive

Summary: Facebook has explained why a comment made by Robert Scoble earlier today was blocked for being "irrelevant or inappropriate." The social networking giant is blaming it on a spam false positive.

SHARE:
15

Facebook just called to tell me the Robert Scoble comment that was blocked earlier today was most likely a false positive caused by an automatic spam filter. Facebook engineers are currently looking into what triggered it.

The spokesperson I talked to wasn't sure what caused the flagging, but may have been a combination of factors, such as the number of links, the length of the post, the number of comments on the post, and so on. None of these make sense to me, however, since I was able to post Scoble's exact comment myself, on the same post in question: here.

If you're just tuning in, make sure to read my earlier article from today: Is Facebook blocking 'irrelevant or inappropriate' comments? Essentially, it appears Facebook has started blocking comments it deems "irrelevant or inappropriate." What's actually happening is much more nuanced.

I was told this isn't exactly what's happening. Facebook's algorithms for comments made on Subscriber posts are apparently much pickier because anyone can reply to a public Facebook post. To be honest, I only find that slightly more comforting.

Here's the error Scoble received when trying to comment:

This comment seems irrelevant or inappropriate and can't be posted. To avoid having your comments blocked, please make sure they contribute to the post in a positive way.

Here's the comment in question:

I'm so glad I didn't start a media business. It's actually really tough to get new and interesting stories and to avoid falling into drama. People forget that Techcrunch was built step-by-step as a new publishing form was taking shape. PandoDaily doesn't have that advantage and, is, indeed, facing competition from social networks that is quite good indeed.

I no longer visit blogs. I watch Twitter, Google+, and Facebook, along with Hacker News, Techmeme, Quora. These are the new news sources.

Plus, Pando Daily actually doesn't have enough capital to compete head on with, say, D: All Things Digital or The Verge, both of which are expanding quickly and have ecosystems behind them.

I was promised an official statement from Facebook. I will be updating this post when I get it, which I was told would take up to an hour from when I got the call (at about 2:00 PM PST).

Update at 2:30 PM PST: That was quick.

"To protect the millions of people who connect and share on Facebook every day, we have automated systems that work in the background to maintain a trusted environment and protect our users from bad actors who often use links to spread spam and malware," a Facebook spokesperson said in a statement. "These systems are so effective that most people who use Facebook will never encounter spam. They're not perfect, though, and in rare instances they make mistakes. This comment was mistakenly blocked as spammy, and we have already started to make adjustments to our classifier. We look forward to learning from rare cases such as these to make sure we don't repeat the same mistake in the future."

This doesn't explain why my copy of Scoble's comment went through. I've asked for further clarification.

Update at 2:35 PM PST: Facebook PR got in touch with Scoble as well, and he posted in the comments section of this article (link). I've added his post to this article for reference, as it clears up quite a bit of the confusion:

Facebook PR responds.

I just talked with Facebook PR about my "comment censorship issue." They say what actually happened is my comment was classified as spam. He further said that this was a "false positive" because my comment was one that Facebook doesn't want to block.

Turns out that my comment was blocked by Facebook's spam classification filters and that it wasn't blocked for what the comment said, but rather because of something unique to that message. They are looking more into it and will let me know more later, after they figure out what triggered it. Their thesis is that my comment triggered it for a few reasons.

It clears up quite a bit of the confusion surrounding the block:

1. I'm subscribed to @max.woolf https://www.facebook.com/max.woolf and am not a friend of his in the system. That means that the spam classification system treats comments more strictly than if we were friends.

2. My comment included three @ links. That probably is what triggered the spam classification system.

3. There might have been other things about the comment that triggered the spam system.

The PR official I talked with told me that the spam classification system has tons of algorithms that try to keep you from posting low-value comments, particularly to public accounts (er, people who have turned on subscriptions here on Facebook).

I actually appreciate that Facebook is trying to do something about comment quality. I had to recently change my privacy settings to only allow friends of friends to comment on my posts because I was getting so many poor comments on my posts (when I did that the poor quality posts instantly stopped).

The PR person also said that a team is looking into why this message got a false positive, and will be adjusting the algorithms to let messages like these get through the system.

Also, the error message made it sound like the message was blocked because of the content of the message, not because it looked spammy. They are looking into the wording of the error and will update that to make the error clearer as to what's going on and why the spam classification system got kicked in.

More as I learn more.

See also:

Topic: Social Enterprise

Emil Protalinski

About Emil Protalinski

Emil is a freelance journalist writing for CNET and ZDNet. Over the years,
he has covered the tech industry for multiple publications, including Ars
Technica, Neowin, and TechSpot.

Kick off your day with ZDNet's daily email newsletter. It's the freshest tech news and opinion, served hot. Get it.

Talkback

15 comments
Log in or register to join the discussion
  • Facebook PR responds to me:

    Facebook PR responds.

    I just talked with Facebook PR about my "comment censorship issue." They say what actually happened is my comment was classified as spam. He further said that this was a "false positive" because my comment was one that Facebook doesn't want to block.

    Turns out that my comment was blocked by Facebook's spam classification filters and that it wasn't blocked for what the comment said, but rather because of something unique to that message. They are looking more into it and will let me know more later, after they figure out what triggered it. Their thesis is that my comment triggered it for a few reasons:

    1. I'm subscribed to @max.woolf https://www.facebook.com/max.woolf and am not a friend of his in the system. That means that the spam classification system treats comments more strictly than if we were friends.

    2. My comment included three @ links. That probably is what triggered the spam classification system.

    3. There might have been other things about the comment that triggered the spam system.

    The PR official I talked with told me that the spam classification system has tons of algorithms that try to keep you from posting low-value comments, particularly to public accounts (er, people who have turned on subscriptions here on Facebook).

    I actually appreciate that Facebook is trying to do something about comment quality. I had to recently change my privacy settings to only allow friends of friends to comment on my posts because I was getting so many poor comments on my posts (when I did that the poor quality posts instantly stopped).

    The PR person also said that a team is looking into why this message got a false positive, and will be adjusting the algorithms to let messages like these get through the system.

    Also, the error message made it sound like the message was blocked because of the content of the message, not because it looked spammy. They are looking into the wording of the error and will update that to make the error clearer as to what's going on and why the spam classification system got kicked in.

    More as I learn more.
    Scobleizer
  • I wonder if celebrity bears the trick...

    If someone of lesser fame had a post censored erroneously, would the error be so quickly and courteously addressed? I sincerely think not. John Doe? Who gives a hill of beans?
    fjpoblam
  • Same thing happens here

    I wrote an on-topic, reasonable comment to this article. It got zapped by the censor bot. No swear words, no links, nothing to give a clue as to why. I hate automated censors.
    Robert Hahn
    • And that should be the Take Home Lesson:

      Moderating posts is hard. Too hard for machines to do -- until one passes the Turing Test;) Why, humans have a hard time doing it anywhere close to well.
      mejohnsn
      • RE: the Take Home Lesson

        [s]Failbook[/s]Facebook is a waste of time.
        fatman65536
  • My sympathies

    but this sort of thing is one of the many reasons I despise and refrain from social media such as Twitter, Google+ and Facebook.
    Claverhouse
  • Oh please!

    ???"it wasn???t blocked for what the comment said, but rather because of something unique to that message. They are looking more into it and will let me know more later, after they figure out what triggered it." As if they don't know! They don't want to *tell* people what triggers blocks, in order to keep people guessing and self censoring. I lost my privilege to tag once, because I "over tagged" a photo, (it made a political point I wanted to spread quickly). There is no stated guideline as to what constitutes too many tags, or else I would have stopped at exactly the limit to avoid getting cut off. Also, they didn't tell me when my priveledges would be restored, but warned me that if I tried to tag before they were restored, the ban would be extended! So I waited a very long time before I attempted to tag again, and I dramatically curtailed my tagging, and I haven't multiple tagged since then, though, I am just realizing this last fact now. They want to quell the rapid spread of information, to slow protest movements, discourage circumventing the official stories of the main stream press, etc, and chilling warnings like this one (link), arbitrary tag limits, and non specific ban times, are all ways they psych us into censoring ourselves. https://www.facebook.com/photo.php?fbid=3557067809877&set=a.1142132998016.21878.1368203483&type=3
    sutragrub@...
    • Well, lesson learned.

      Well, lesson learned - keep the number of tags down. They probably should have guidelines for it, I agree.

      I seriously doubt they're trying to "quell" you - you have plenty of political stuff that [i]has[/i] gone through. Reading your timeline shows plenty of politics. A bit too much of a tin foil hat for my taste, but your message is generally getting through.
      CobraA1
    • Big Brother got trolled as a child...

      That's exactly the reason I am not a fan of Facebook. All the efforts to PC this social channel seem like the childish whining of a newb who's been trolled one too many times and never learned to deal with it.
      RyuDarragh
  • Tin-foil hats don't only ward off mind-control; they allow *potential*

    As I wrote in http://mbalog.robincheung.ca/farcebook-cens0ring-gymnastics/ for having a comment blocked for a "spammy link," when my post didn't even have a Link, nor anything that could plausibly be considered "spammy," I have to call attention to the idea that just because one wears a tin-foil hat to ward off mind-control rays, it doesn't mean that its true use isn't apocryphal until a later date (or, as John 20:29's reply to Doubting Thomas' "Dominus meus et Deus meus!" be paraphrased, "Thomas be blessed; for you saw and believed, but even more blessed be those who believed and did not have to find out cens0ring was already institutionalised through their own apathy.")

    If it be a spam post, Farcebook already has a CAPTCHA system in place to verify that it is a human sender; beyond that, it doesn't matter what the content is because it's not up to Farcebook to determine if it is acceptable beyond any extant but cryptic disclaiming Acceptable Use type policies.

    RobIncAMDSPhD http://RobinCheung.ca/
    RobIncAMDSPhD
    • Actually . . .

      Actually . . .

      The phrase Jesus responds with doesn't actually say "Thomas be blessed; ...," it's more like "Have you believed because you have seen me? Blessed are those who have not seen and yet have believed." (NIV, KJV has a similar translation)

      Interestingly enough, "Dominus meus et Deus meus!" seems to be a latin translation of the original Greek "mou kyrios kai mou theos." Not unusual, since Latin was used a lot in the Catholic Church.

      It may be nice, perhaps useful, to discuss such scenarios, however they generally provide biased information and slanted interpretations of evidence. Conspiracy theorists tend to ignore or ridicule evidence that doesn't fit in with their idea of how things "REALLY???" happened. When all is said and done, the core of conspiracy theories tend to be heavily centered around the idea of evil motives, and as such assume a lot about the way people think.

      I have found that most of the time, the real answer is unlikely to be bad intent, but rather it's almost always something rather mundane.

      Not saying conspiracies can't happen, but [i]usually[/i] the best explanation is the one that gives the benefit of the doubt.
      CobraA1
  • Blocked by Facebook [reposting earlier comment]

    I got the dreaded Facebook Warning after leaving the following comment on (old pal) Tony Maakie's post about chickens being found with caffeine in their feathers:

    "As someone who in a former life actually was a chicken, I'd like to strongly object to the arrogant assumption by pampered human beings with double vowels in their names that chickens don't appreciate coffee. We do! In fact, it's common knowledge that coffee beans were first plucked out of the soil by enterprising chickens -- long before humans even stopped swinging in trees."

    http://chicagolibrarian.com/node/873
    leoklein
    • Good One!

      I guess the censorbots can't handle irony and sarcasm. No surprise, seeing how many people have trouble sensing it!

      And I really like your example. In fact, I think the people at Facebook who demand posters "be more positive" should also be reincarnated as chickens -- and denied coffee!
      mejohnsn
  • addy80

    While this subject can be very touchy for most people, my opinion is that there has to be a middle or common ground that we all can find.landlord attorneys in nyc
    I do appreciate that youve added relevant and intelligent commentary here though. Thank you!
    addy800
  • www.newnhljerseyssupply.com

    Cheap NHL jersey
    nhl home jerseys
    nhl road jerseys
    nhl jerseys for sale
    Anaheim Ducks
    Boston Bruins
    Buffalo Sabres
    Calgary Flames
    Carolina Hurricanes
    Chicago Blackhawks
    Colorado Avalanche
    Columbus Blue Jackets
    Dallas Stars
    Detroit Red Wings
    Edmonton Oilers
    Florida Panthers
    Los Angeles Kings
    Minnesota Wild
    nhlhomejerseys