SEO

Google Patent : Organic Results Ranked by User Profiling

Google Patent : Organic Results Ranked by User Profiling

Google has filed for an organic search patent, termed Personalization of placed content ordering in search results, to serve organic search results based on user profiles. Google has also applied for a similar behavioral targeting patent for its advertising network, but this seems to be a first from Google with plans to integrate user profiling into natural search ranking.

Such profiles are created by Google and gathered from previous queries, web navigation behavior via tracked links and possibly sites visited which serve Google ads, computers with Google Applications installed such as Desktop Search, Google Wi-fi Connection or Sidebar, and personal information which Google identifies which may be “implicitly or explicitly provided by the user.”

This new ranking system, which is a spin off of PageRank and the current Google ranking algorithm, could be referred to as Profile Rank. What is the difference between this new ranking system and Google Personalized Search? Personalized Search was beta tested by Google users who have opted in to Google profile building while the new Profile Rank is based upon user profiles built by tracking a users web habits in and outside of Google Search, even if the user has not opted in to be served personalized results or is a registered Google Account member : Wide Spread Personalization to all users.

In the patent application Google explains that when a search engine generates search results in response to a search query, a listed site which satisfies the query is assigned a query score, QueryScore, in accordance with the search query. This query score is then modulated by the site’s PageRank, to generate a generic score, GenericScore, that is expressed as : GenericScore=QueryScore*PageRank.

However, Google states that the GenericScore system may not be relevant enough and proposes a more in depth Profile Rank (PersonalizedScore) : This GenericScore may not appropriately reflect the site’s importance to a particular user if the user’s interests or preferences are dramatically different from that of the random surfer. The relevance of a site to user can be accurately characterized by a set of profile ranks, based on the correlation between a sites content and the user’s term-based profile, herein called the TermScore, the correlation between one or more categories associated with a site and user’s category-based profile, herein called the CategoryScore, and the correlation between the URL and/or host of the site and user’s link-based profile, herein called the LinkScore. Therefore, the site may be assigned a personalized rank that is a function of both the document’s generic score and the user profile scores. This personalized score can be expressed as: PersonalizedScore=GenericScore*(TermScore+CategoryScore+LinkScore).

Google gives an example of a listing based upon user profiling mixed with information given by the user : a user may choose to offer personal information, including demographic and geographic information associated with the user, such as the user’s age or age range, educational level or range, income level or range, language preferences, marital status, geographic location (e.g., the city, state and country in which the user resides, and possibly also including additional information such as street address, zip code, and telephone area code), cultural background or preferences, or any subset of these.

Compared with other types of personal information such as a user’s favorite sports or movies that are often time varying, this personal information is more static and more difficult to infer from the user’s search queries and search results, but may be crucial in correctly interpreting certain queries submitted by the user.

For example, if a user submits a query containing “Japanese restaurant”, it is very likely that he may be searching for a local Japanese restaurant for dinner. Without knowing the user’s geographical location, it is hard to order the search results so as to bring to the top those items that are most relevant to the user’s true intention. In certain cases, however, it is possible to infer this information. For example, users often select results associated with a specific region corresponding to where they live.

What about shared machines? If the one computer is shared by various users with different web behavior, how is Google to define Profile Rank in its organic search results? Google has thought this though :
Sometimes, multiple users may share a machine, e.g., in a public library. These users may have different interests and preferences. In one embodiment, a user may explicitly login to the service so the system knows his identity. Alternatively, different users can be automatically recognized based on the items they access or other characteristics of their access patterns. For example, different users may move the mouse in different ways, type differently, and use different applications and features of those applications. Based on a corpus of events on a client and/or server, it is possible to create a model for identifying users, and for then using that identification to select an appropriate “user” profile. In such circumstances, the “user” may actually be a group of people having somewhat similar computer usage patterns, interests and the like.

Users identified by the way they move a mouse or typing style? Amazing.

The patent, Personalization of placed content ordering in search results, is pretty detailed and deep. I suggest running over it a couple of times, printing it out and breaking out the highlite marker from college because there is a lot to it and a handfull of clues as to the future of Google and its ranking system.

Screen Shot 2014 04 15 at 7.21.12 AM Google Patent : Organic Results Ranked by User Profiling
Loren Baker is the Founder of SEJ, an Advisor at Alpha Brand Media and runs Foundation Digital, a digital marketing strategy & development agency.
Screen Shot 2014 04 15 at 7.21.12 AM Google Patent : Organic Results Ranked by User Profiling

Comments are closed.

21 thoughts on “Google Patent : Organic Results Ranked by User Profiling

  1. You say “a first from Google with plans to integrate user profiling into natural search results”, which makes it looks like Google wanted to put sponsored results right into their organic results. But nowhere in the “Personalization of placed content ordering in search results” patent can I see that. Google already personalizes my organic search results, but not to include sponsored results — just to include different organic results. And now, apparently, they filed a patent to rank ads the same way. So that would mean the personalization feature is extended to the right-side AdWords ads.

    Maybe I misunderstood you. And of course, if it would indeed mean anything else — paid results right in the organic ones, without special mention or formatting in the result — it would be a major scandal. I just don’t see a sign of that in the first linked patent.

  2. Nope, according to the patent the organic results will change due to user profiles. Like personalized search, except for everybody – not just the people who have opted into personalized search, like yourself.

    No mention of sponsored results mixed in with organic.

  3. I thought “placed content” (as in the Google Patent” was an euphemism for “sponsored results”. So I suppose that was wrong then. But then why did you say this was something we expect from their AdWords or AdSense divisions? And why (elsewhere) did you say it’s “shocking”? Please explain & excuse my misunderstandings…

  4. Well, I’d expect them to do total mass user profiling with their advertising network and not with organic. Doing so with organic would be a total overhaul of their current algo.

    The current algo would just be a part of the equation, along with surfer behavior and location.

    If you and I searched for the same key term from our computers, we could see totally different results based on our behavior and locale.

    Essentially, what they are proposing is a change of the algo to make it more dynamic, which would really throw a wrentch into SEO rank tracking, because even if a site is #1 or #3 in the normal algo, with Profile Rank running, such a site might not even make it to the first page.

    So, I’m shocked by the notion of the overhauling of their results serving system. I would not be shocked at an update, or a dance, but when they pull the carpet from under everyone’s feet with the new results system, many will be shocked.

    I think I’ll strike that bit about AdWords & AdSense as that can be confusing ;)

  5. If Google took this approach would it not then change from the ‘World Wide Web’ to the ‘Local Web’? I would then be getting my results for my search which is excluding your #1 & #3 results above. Now this can be an issue for me if I were actually looking for one of those ‘way out there’ kind of searches that I knew was on the other side of the world. And now all I get in my results is the local shopping centre down the road from me. Go for it Google, it will give us a choice to stop selling our soul to you for your ‘Evil’ world domination and give us all the chance to spread out and distribute our searching equally among all the search providers out there.

  6. Thanks for clearing it up, and neverind my confusion. Actually, I don’t like personalized results at all (I want to see what everyone else sees, and my interests change — I don’t want to be stuck seeing only “my side” of the world), or if they want to have it, they should always make it optional (I guess you could always sign out/ delete your cookies to turn it off).

  7. Hmm, that worked. Too long? Here it is in chunks then:-

    Philipp, you’re not wrong that “placed content” means ads, it’s just that it means both personalized search results and ads (and more) :-

    “When search results are returned to a user in response to a search query, often times certain placed content is returned as well. Placed content is usually in the form of advertising, but could be any type of content related to the search query or to a document being sent to the user.”

    And it’s apparent that they contemplate both personalized and organic results being shown together (at least sometimes), by this section :-

    “In one embodiment, the generic search results and personalized search results are interleaved, with the odd positions (e.g., 1, 3, 5, etc.) of a search results list reserved for generic search results and the even positions (e.g., 2, 4, 6, etc.) reserved for personalized search results, or vice versa. […] More generally, generic search results are intermixed or interleaved with personalized search results, so that the items in the search results presented to the user include both generic and personalized search results.”

  8. But though Loren is right that this filing is about, well, Organic Results Ranked by User Profiling, it also does have a great deal to say about AdWords & AdSense ranked by user profiling too (at least as much, in fact). If profiling tells Google to push search results about gadgets for you, and food for me, when we search [blackberry], then it will also do the same for the ads we (respectively) see :-

    “It would be desirable to increase the likelihood that the user is presented with ads that are of interest to the user. Accordingly, ads which are in some way related to the user’s profile are better candidates for presentation. One way to do this is to modify the ad’s score based on the similarity of the ad to the user’s profile. Referring back the broader term, “placed content,” FIG. 11 illustrates one embodiment for providing placed content with search results.”

  9. I have a keyword filter for anti-sp@m purposes, perhaps your post is held in moderation, I’ll check.

    Ok Milly, I think the meatiest comments are approved. Not sure which word held them in moderation. Something to look into on my side :)

  10. Phillip, the patent was filed by Google’s Patent Filing and Intellectual Property law firm under the name of some of the top Google Search Engineers; apparently common practice in patents not to file directly under the company’s name.

  11. As is common practice with patents, Google has thrown in the kitchen sink. It is highly unlikely that they have any plans or ability to id users by typing styles or mouse movement.