Tech, Autos, & Gear in Layman's Terms Since 2006

385

July 9, 2013 • Rants and Raves

Bing’s SafeSearch Filter Issues Explained!

Bing's SafeSearch Filter Issues Explained!

A few days ago I pointed out some very odd behavior in the Bing SafeSearch filter. Certain words, like “Lesbian” were being summarily blocked, while insulting or hateful words came through just fine. I had the chance to chat with someone from the Bing SafeSearch team today, and I learned a few important things: One, the SafeSearch filter isn’t as simplistic as it first appears, and there’s some nuance to how it blocks content. And two, Microsoft is an incredibly responsive and community oriented company!

I learned that SafeSearch is designed to filter out “adult” content from web results. If a web result returns too many pornographic or adult links, the filter assumes the other links are suspect, and blocks the whole search. Apparently even innocuous terms get caught up in this, as the term “homemade” gets flagged and blocked on SafeSearch (and after I searched “homemade” with SafeSearch off, I understand why!)

Words like “faggot” may be offensive, but they don’t bring up adult content as the top links, mostly slang definition sites and Wikipedia. The algorithm is entirely automatic, and it depends on what links are highly ranked; in other words, what’s verboten today may not be tomorrow if the top links change, and vice versa if some particularly everyday keyword in pornography descriptions were to pop up.

As part of the development of SafeSearch, the team hopes to find a way to add safe alternative terms. This way, if a search for “homemade” was blocked, it might come back and say “have you tried ‘homemade cupcakes’ instead?” SafeSearch also relies on context and natural language, which is why results like “Gay, Lesbian, Straight Education Network” sails through easily; it’s a specific term, and there’s no adult content attached to it (yet, anyway– apparently the Internet really is just a race between actual content and pornography). And because Bing’s algorithm is dynamic, as real content pushes down porn sites, the items caught by the filter will change and adjust. There is no blacklist of terms or anything similar, so context is really key in what gets flagged and what does not.

All of this was actually pretty fascinating, and it gave me a great deal of insight into how much work Microsoft has put into — and is continuing to put into — Bing.

But what struck me was how genuinely concerned my contact at Bing was that I knew that Microsoft was a very gay and lesbian friendly company, that they were very concerned about me being distressed or offended, and that they made sure I not only hung up with a better understanding of how SafeSearch works, but also that I really knew that Microsoft hadn’t set out to offend anyone.

What really impresses me is that someone at Microsoft cared enough about my experience to reach out and have a discussion. It gave me a whole new insight into the ways Bing is dynamic and still growing, and it gave me a whole new respect for Microsoft and their corporate culture. Hopefully SafeSearch will be able to implement safer suggested terms to help alleviate SafeSearch issues; in the meantime, if you hit the SafeSearch filter as a result of a search, try reworking your query. My original query “lesbian mom blogs” works just as well as “gay mom blogs” or “LGBT mom blogs”, for example, and now that I know the context of why that is the case, ┬áit makes more sense.

And remember, don’t search Bing for “homemade” with SafeSearch on … it’s not just for cupcakes!

 

Related: Bing Thinks Lesbian Is a Dirty Word

 

5 Responses to " Bing’s SafeSearch Filter Issues Explained! "

  1. Absolutely awesome! Been very impressed with many things from Microsoft, and seeing how they are handling this earns them even more kudos!

  2. Michael Roselius says:

    What I like to do is find something mildly frustrating, write an inflammatory post on a well read blog about it, turning it into some sort of manufactured injustice and THEN do my research and find out the details – which I can post in a follow-up article.

    I appreciate that you at least took the effort to learn the truth about what is happening w/ your search – and write about it – but I am disappointed that you didn’t research the story fully before you posted about it. By writing this up the way you did, you fan the flames of a non-issue, create this emotional controversy, and then in a follow-up pour water on the whole thing. It reads as cheap sensationalism and unfortunately, we’ll never know the percentage of readers who read the first article but never read the followup and are left with the perception that MSFT is not who they are.

    And let’s be clear – i’d be just as disappointed if you were trashing the effectiveness of a waterproof Otterbox case that you later discover you assembled incorrectly. The substance of your article is not my complaint – it’s the fact that you fired your first shot WAY too early and before you really understood the product (Bing) that you were trashing.

    • Carly Z says:

      To be fair, I had no idea that there was a reasonable explanation. I was just frustrated because it made no sense.
      It was actually an accident of networking that led to the answer, thanks to a friend who knew someone…the original post was not designed to get someone to respond, it was me being frustrated because I couldn’t wrap my head around how a hateful word came through while a more mainstream one got caught.
      I literally wrote the followup as soon as i had an answer…but i wrote the initial post without knowing i would have an answer. And i would never have guessed the answer boiled down to “porn links”. We will make sure there’s a link to the followup on the initial post.
      As much as it would be great to wait and research it, this was a weird enough glitch that i wanted to share it asap…just like i shared the followup as well.
      Sent from my Windows Phone

      • dancohen says:

        The explanation is fine but it does lend itself to making an impression that is not a good one. I would have been happier if the result was a commitment to changing the warning notice’s wording to say something like “This warning may not be the result of the term you actually used but reflect related searches that may be inappropriate. As a precaution however we have set filters to offer up this warning. We prefer to err on the side of being safe.”

        Here’s the other thing- to which you alluded Carly- you aren’t the normal person using Bing. You have a depth of knowledge with regard to tech and contacts that can give you insight and, as in this case, give some surprising insight into the issue. MOST people using Bing would simply use the search engine and get the initial results you got. They WOULD be left with the initial impression you got and for good reason. That IS an issue.

        Moreover, in hindsight it is easy to say, “Well after doing research there is a reason for this” but none of us expected you would get such insight… and as quickly as you did.

  3. […] Update 07/09/13: Please see Microsoft’s Response […]

Leave a Reply