Bing: 130 Million URLs Removed For URL Keyword Stuffing

Bing posted something you'd never see from Google, the details around how they detect and filter out spammers who use keywords in the URLs.

Bing says they detect keyword stuffing in URLs via many methods but detailed these:

• Site size
• Number of hosts
• Number of words in host/ domain names and path
• Host/ domain/ path keyword co-occurrence (inc. unigrams and bigrams)
• % of the site cluster comprised of top frequency host/ domain name keywords
• Host/ domain names containing certain lexicons/ pattern combinations (e.g. [“year”, “event | product name”], http://www.turbotaxonline2014.com)
• Site/page content quality & popularity signals

They actually documented that they rolled out a massive update that impacted about 3 percent of search queries, about 5 million sites, and 130 million urls specifically around the URL keyword stuffing spam filter. They said this resulted "in upwards of 75% reduction in traffic to these sites from Bing." Now, to really blow your mind, Bing shared some keywords they saw this for often including {hotmail login}, {bestbuy on sale}, {cheap hdtv} and even provided examples of spam sites impacted including www.cheapviagrausa.com, www.cheapviagrapharma.com, www.buyviagracheapviagraergr.com and www.gmailloginsigninup.com.

Nice job Bing, please give us more of this.

Forum discussion at WebmasterWorld.