"Phrase Based Re-Ranking" Algorithm To Blame for the Google 950 Penalty?

Feb 8, 2007 • 7:59 am | comments (11) by twitter Google+ | Filed Under Google Search Engine Optimization
 

There has been a lot of recent talk about the Google Minus-950 Penalty. It was named that because people didn't find their pages anywhere before around the 950th result. The question is what happened recently to cause such a change in their rankings at Google.com?

WebmasterWorld administrator, tedster, believes that it has to do with a new patent application by Anna Lynn Patterson of Google named Detecting spam documents in a phrase based information retrieval system. There is a large conversation about that patent application at WebmasterWorld. It basically says, in short:

Phrases are identified that predict the presence of other phrases in documents. Documents are the indexed according to their included phrases. A spam document is identified based on the number of related phrases included in a document.

Tedster broke off the original thread on the 950 penalty and created a new one at WebmasterWorld on "Phrase Based Re-ranking." Tedster feels it is the Phrase Based Re-ranking algorithm that is the cause for the minus 950 effect. Tedster explains, "What it seems to be is some kind of "Phrase-Based Reranking" - possibly related (we're still probing here) to the Spam Detection Patent invented by Googler Anna Lynn Patterson." Let me pull more quotes from the thread to clarify his theory.

It's like getting a poor health symptom in one area of your body from not having enough of some important nutrient -- even though you've got plenty of others and plenty of good health in many ways.

In one case I know of, the signs of this problem disappeared with one solid new inbound link from a very different domain, with the problematic phrase used as the anchor text. By "very different" I mean the linking domain was not in the 1,000 for the given search.

So, not less "SEO" fixed it, but more. The purely OOP assumptions don't sit right with me, given this anecdotal result. Now it's only one case, so it's certainly not "proof" of anything, but the fix has now been stable for several data refreshes at Google, so it is a decent data point to keep in mind.

Of course this is just a theory and that is why these threads are fun. Nice work tedster!

Forum discussion at WebmasterWorld.

Previous story: Google's Email, Gmail, Is Now Open To Public
 
blog comments powered by Disqus