T3 SEO BLOG

In some instances, a user’s unique identifier may be used to rank search based on the relationships between a user and the content providers. For example, a user may search for a specific term and explicitly or implicitly provide his unique user identification to the search engine. The results of the search may be ranked such that the user’s friend’s content may be highlighted or merely higher ranked in the search results. Presumably, the user may have an interest in results that come from sources with whom he has a preexisting relationship.

By associating content with metadata that includes a content owner’s network of friends, the metadata may be used by specialized and general purpose search engines to find relevant and pertinent results for a specific content owner.

Google could be using a very similar way to gather data from social networks as a way to rank content connected to a user from that data, by “degree of separation”.  Now, we take a look at their personalization patent in order to get an understanding of how they could put this all together for their personalized search results engine.

How Does Googles Personalized Search Work?

The 2nd patent I mentioned above deals with the 3 profiles Google uses to help determine personalized search results.

In the patent they mention category, term, and link profiles.  Here is how they are defined in the patent:

Each sub-process produces one type of user profile characterizing a user’s interests or preferences from a particular perspective. They are:

• a term-based profile 231—this profile represents a user’s search preferences with a plurality of terms, where each term is given a weight indicating the importance of the term to the user;
• a category-based profile 233—this profile correlates a user’s search preferences with a set of categories, which may be organized in a hierarchal fashion, with each category being given a weight indicating the extent of correlation between the user’s search preferences and the category; and
• a link-based profile 235—this profile identifies a plurality of links that are directly or indirectly related to the user’s search preferences, with each link being given a weight indicating the relevance between the user’s search preferences and the link.

How Google calculates a “generic” and “personalized” score for documents/content:

When a search engine generates search results in response to a search query, a candidate document D that satisfies the query is assigned a query score, QueryScore, in accordance with the search query. This query score is then modulated by document D’s page rank, PageRank, to generate a generic score, GenericScore, that is expressed as

GenericScore=QueryScore*PageRank.

This generic score may not appropriately reflect document D’s importance to a particular user U if the user’s interests or preferences are dramatically different from that of the random surfer. The relevance of document D to user U can be accurately characterized by a set of profile ranks, based on the correlation between document D’s content and user U’s term-based profile, herein called the TermScore, the correlation between one or more categories associated with document D and user U’s category-based profile, herein called the CategoryScore, and the correlation between the URL and/or host of document D and user U’s link-based profile, herein called the LinkScore. Therefore, document D may be assigned a personalized rank that is a function of both the document’s generic score and the user profile scores. In one embodiment, this personalized score can be expressed as:

PersonalizedScore=GenericScore*(TermScore+CategoryScore+LinkScore).

How profile confidence determines personalized results:

In another embodiment, the personalized ranks and generic ranks are further weighted by a user profile’s confidence level. The confidence level takes into account factors such as how much information has been acquired about the user, how close the current search query matches the user’s profile, how old the user profile is, etc. If only a very short history of the user is available, the user’s profile may be assigned a correspondingly low confidence value. The final score of an identified document can be determined as:

FinalScore=ProfileScore*ProfileConfidence+GenericScore*(1−ProfileConfidence).

When intermixing generic and personalized results, the fraction of personalized results may be adjusted based on the profile confidence, for example using only one personalized result when the confidence is low.

Connection Between Google Personalization and Google+

I researched these patents in early 2012 after Google announced “Search Plus Your World” which was the initial launch of full scale integration of Google+ data within their core search engine results.  After reviewing the patents it was clear Google+ is the conduit directly into Google’s personalization profiles and should be utilized as such.  Using Google+ you can help “directly connect” (1st degree connection) your website, brand, products or services directly into users personalized profiles.  

Here is a slide I created with the elements I felt (and still do) were most important to “personalized rank” and that could be developed with Google+:

Here is a slide I created to demonstrate how/where on a Google+ page  you can feed data directly into the 3 personalization profiles of individuals:

Power of Using Google+ Links

Google mentioned within their official announcement of Search Plus Your World that content within Google+ would be highlighted within personalized search results.  However, what was going to be powerful was if I could utilize Google+ to drive a websites content to the top of Google’s personalized search results.

During this time I began to notice that websites that were linked to from Google+ pages that I was following were being pushed to the 1st page of my personalized results.

Here is an example of a site that moved from page 2 to spot #4 in my personalized results.  I was following the Google+ page of the site, but the Google+ page had no posts and only had a link back to the website.

Here is an example of another domain that was pushed to the top of my personalized results.  This domain was only linked to from within the Google+ page I was following, no posts, no shares, no +1’s.

The above examples are from early 2012, so here are some current 2013 examples just to demonstrate that Google+ links still have power to push websites to the top of personalized results.

Below is an example of a website that I’m not following within Google+, but it is pushed to the 1st page of my personalized results just because someone I am following linked to it! Yes, technically it was “shared” on Google+, but what I’m trying to focus on is it was just a link to a website!

Here is the post that contains the link to the site causing it to be pushed to the 1st page of my personalized results:

Let’s Sum Things Up

Hopefully, this post will help explain how Google+ is the direct conduit into Google’s personalization profiles and how it can be used effectively to build value for brands, services and companies.  As we should all know by now, more and more people are “logged in” to Google+, so they will see personalized results, unless they turn the feature off of course.

It is becoming increasingly important to build connections with your targeted markets and demographics in order to take advantage of Google’s shift to personalized search results and the vast number of people who will be “logged in” to Google+ because of Android, YouTube, Gmail, etc.

A few takeaways:

1. Google+ is the primary method that Google gathers DIRECT social meta data.
2. Google is using social meta data from Google+ to build personalized profiles of individuals.
3. Social meta data from Google+ has a direct impact on personalized search results because of the personalized profiles Categories, Terms, and Links.
4. Links within Google+ create direct connections (within personalized link profiles) that can drive “non-Google+” content to the 1st page of personalized results!
5. Start using Google+ to build DIRECT connections with your target markets or demographics in order to associate your products, services, or brand within their Google personal profiles (category, term, links).

What are your thoughts, have you been seeing non-Google+ content showing up in your personalized results?