An Algorithm For Finding, Killing Spam

Since the launch of Blekko, we have had a clear mission; and that is to eliminate spam from web search. With thousands of slashtags created by our users to help reduce spam, we are making quick and significant progress in achieving our set goals.

In the past, our efforts to clean-up search have included our partnership with the Stack Overflow community, and our public banning of the top 20 sites most users marked as spam at Blekko.

Today, we are taking the next giant step forward with the launch of Blekko’s new AdSpam algorithm. This new technology will dramatically change search. It’s the first search algorithm ever created to find spam rather than rank results. The algorithm is specifically designed to recognize pages which are spam and eliminate them before they ever appear in search results.

Blekko has used the AdSpam technology to eliminate more that 1.1 million domains that support multi-millions of pages.

So what is exactly is AdSpam? In short, it is a machine-learning algorithm that examines pages for a specific spam signals — the presence of multiple display ad positions on a single page and thin to zero content. Unlike algorithms used by other search engines, AdSpam is being used in conjunction with human curation to detect to continue the War on Spam.

So in a time where spam-free search is becoming increasingly important, you can be sure that Blekko’s new AdSpam technology will scan every new page on the Web before it gets added to Blekko search results. We believe the way to better search results is by using an algorithm that was created to kill spam, not just crawl it.

Coverage here:

New York Times


Search Engine Land

This entry was posted in Technology. Bookmark the permalink.

17 Responses to An Algorithm For Finding, Killing Spam

  1. Pingback: Blekko Blocks More “Spam” Domains: 1.1 Million Of Them

  2. Sholto says:

    so this is a great idea although my own site which is not MFA but uses google doubleclick to host advertising has been caught in the filter. It is an obvious idea and needs some more tweaking since there are many good sites that are carefully curated and use advertising to support them which is not a bad thing in the wider scheme when they add value.

  3. Pingback: One Million Fewer Things to Worry About: ‘Blekko’ Search Engine Kills Off Spam Sites - Techland -

  4. Love it, love Blekko, keep it up guys

  5. Flash Games says:

    Thank you..really informative!!

  6. buzzIT says:

    can we get to see the bigger sample of those 1.1 million sites?

  7. Waltraut says:

    I would really like to give thanks very much for that work you have made in writing this piece of writing. I am hoping the same top work from you in the future as well.

  8. Jag says:

    Keep going. Now more people would love and use blekko. Start with some marketing campaign that can reach all sort of users.

  9. Hafna says:

    Would be great to see some of the blocked domains…

  10. freesoft says:

    Thank you..really informative!!

  11. Zachariah says:

    Many thanks for finding the time to explain the terminlogy for the starters!

  12. Switched to Blekko today after being a watcher for a while. Will try and get some slashtags done later in the week.

  13. Tech Crates says:

    Very informative and interesting to read….

  14. Jason says:

    Cutting out spam is good thing but it almost seems an impossible task – Good luck, I look forward to the results.

  15. Pingback: Blekko Identifies Over a Million Domains as Spam

  16. Very informative post. Heightens interest in using Blekko more with a clear understanding about what differentiates Blekko from other search engines. Thank you for sharing insights about your AdSpam technology and benefits for search. Look forward to more coverage on same subject and related in future.

  17. Bridal Swan says:

    Great job, guys. Keep going