New Google Patent - Personalizing Anchor Text Scores

[pageoneresults]

A computer-implemented method of determining a personalized ranking of a document that satisfies a set of query terms, comprising: determining an information retrieval score for the document based on its content and the set of query terms; identifying a set of source documents that have links to the document and that have anchor text satisfying a predefined requirement with respect to the set of query terms; calculating personalized page importance scores of the identified source documents according to a set of user-specific parameters; accumulating a personalized anchor text score for the document as a function of the personalized page importance scores of the identified source documents; and generating a personalized ranking for the document based on its information retrieval score and personalized anchor text score.

Personalizing anchor text scores in a search engine [patft.uspto.gov]

[tedster]

A lot of intentional vagueness and gray area, but it is interesting to note that this patent focuses on anchor text for personalization purposes. But I'm having trouble seeing the "personalization" element in action here.

[pageoneresults]

But I'm having trouble seeing the "personalization" element in action here.

I'm having some difficulty myself even after printing it out and "absorbing" it. Is this related to iGoogle and personalized pages? Are they using the data from those personalized pages as a factor in further determining relevancy of the primary indices?

I was hoping Slawski would be on it but he's at SES right now. :)

[pageoneresults]

For each document in the list, the search engine determines an Information Retrieval Score based on its content and the query terms, and also identifies a set of source documents that have links to the document and that also have anchor text satisfying a predefined requirement with respect to the query terms.

The search engine calculates a Personalized Page Importance Score for each of the identified source documents according to a set of user-specific parameters and accumulates the personalized page importance scores to produce a Personalized Anchor Text Score for the document. The personalized anchor text score is then combined with the document's information retrieval score to generate a Personalized Ranking for the document. The documents are ordered according to their respective personalized rankings.

Emphasis mine. Did you get all that? :)

Here are some Initialisms I put together while perusing the patent...

IRS - Information Retrieval Score
PR - Personalized Ranking
PATS - Personalized Anchor Text Score
PLAS - Personalized Link Analysis Score
PPIS - Personalized Page Importance Score

10. The method of claim 1, wherein the set of user-specific parameters include information concerning websites favored by a user.

Google Bookmarks
Google Reader

[tedster]

Looks like Bill Slawski got back to this topic:

The inventors listed in the patent are Taher Haveliwala, Glen Jeh, and Sepandar Kamvar, and all three came to Google when the stealth startup that they founded, Kaltix, was acquired by the search engine in late 2003. Kaltix was started as a spinoff of the Stanford Personalized PageRank Project [nlp.stanford.edu].

The trio were working on a way to speed up the calculation of PageRank so that a personalized PageRank could be calculated for each searcher. But a personalized PageRank wasn’t their only goal. They also wanted to use other methods to reinforce that personalization, and this patent aims at taking advantage of the meaning of text in the anchor portion of links pointing to pages.

[seobythesea.com...]

The main focus of this patent seems to be practical - improve the speed of calculation, and at the same time, decrease the computing resources needed for the computation.

[edited by: tedster at 5:46 pm (utc) on Aug. 28, 2007]

[pageoneresults]

You have to wonder if Slawski works for the Patent Office. :) That there is some really deep stuff. It takes me a "few reads" before understanding but it appears that I was on track with my initial assumptions. Let's add another Initialism to the mix and possibly the next biggest fad...

PPR - Personalized PageRank™

So, what's your PPR?

Hey Slawski, great job on dissecting that one. ;)