SEO Blog - Internet marketing news and views  

The Art of Personalized Search Optimization

Written by David Harry   
Monday, 03 December 2007 04:14

Making Personalized Search Work for You

Welcome to the final leg of this journey into what Personalized Search is and why webmasters and SEO professionals should take the time to understand it better. This time around we will look at what you can do from an SEO perspective to best leverage Personalized Search Optimization. So far we looked at;

Part I; Why Google’s Personalized Search is important – examining the pervasive nature of Google accounts and Personalized Search now and in the future
Part II; I have seen the future and it is VERY personal – Looks at recent business moves by Google and touches on User Performance Metrics
Part III; What every SEO should know about Personalized Search – takes apart the various methods under the hood.

I have no idea where to begin!?!Sure, this has been a long winded diatribe, but I wanted to make sure that this was not taken lightly. Besides, I started writing and it simply kept growing and growing, the concept was more important than brevity in the end. If you hadn’t come across it, there was some interesting speculation about a recent Google Labs experiment that is worth also reading. It sheds yet more light upon concepts relating to User Performance Metrics (UPMs) in the Google Search kingdom.

Let’s get underway….


User Performance Metrics are Personal

A term we have bandied about a few times during this qudra-post is User Performance Metrics. Whhaaaaatt the...?? Ok, In simplest terms UPMs are data sets a search engine measures from prior information retrieval processes and activities (searches) including query data, user information, and document information. The search engine seeks to get to know you and your preferences better by actively or passively collecting information on what you do.

Not only what you select/interact with from a given set of search results (or the Ads served with them), but what you do not select or have minimal interactions with (bounce rates) can have an effect. These metrics can be used to create a greater probability model for future search result sets. Ultimately the search results could have active user interactions (see Digg-Style) in addition to more passive collection methods (Google desktop, toolbar, IP, cookies, Google account et al).

You can think of it in terms of conversions in many ways. The better a given item performs becomes another factor in deciding what it is and its relative value. So when you think of ‘ranking’ in a world of UPMs you start to move into how best insight interest in a target page beyond merely throwing links at a it with heavy duty keyword densities and targeted title tag. There are a new set of challenges that need to be addressed and added to the play book.


How to Leverage Personalized Search

What is important to conceptualize is that is a land of true ever-flux where not only the actions of a single user, but many (inclusive of user ‘types or groups’), can effect how you rank ultimately. We cannot as readily engage such a system as we would traditionally in the world of SEO. It is also worth mentioning that the usual suspects such as PageRank still apply. The Personalized Search (PS) aspects (or any UPM method) are merely further ranking methods in addition to traditional systems that exist. This is simply one more consideration to be had. The level of concern depends on the weight given such metrics and the prevalence of personalized search over-all. What we’ll be looking at is what areas of existing SEO/Site Development need to be looked at to leverage the challenges that dealing with PSO presents.


Areas for Consideration;

Demographics – you should also be sure to leverage any obvious demographics that may apply to your site. If it is geo-graphic, topical (sports, politics) or even a given age group, ensuring that this is targeted effectively is important in that the ‘topical’ nature of personalized search can group results prior to even ranking them. If your site is not clear in each of these areas, it risks less weighting to tighter demographic starting document sets. Even your off site activities (link building, Social Media Marketing etc..) should be as tightly targeted as possible.

Relevance Profile – of particular interest is potential categorization in terms of topical relevance. Ensuring that your site provides a strong relevance train would be particularly valuable. Much like phrase based indexing and retrieval concepts, probabilities play a large role. When refining results the search engine looks at related probable matches. Through a concerted effort with on-site and off-site relevance strengthening, you increase the odds of making it to a given set of results in a world of ‘flux’. It never hurts to review the concepts surrounding Phrase Based Indexing and Retrieval as many of the related patents addressed deriving concepts/topics from word groupings (ie; phrases).

One would also have to imagine that tightening up the relevance profile in your Social Media Marketing efforts would also be beneficial to a tighter topical link profile. Furthermore, many topically targeted visitors that enter a site may bookmark (or passive collection) your site which ads to the organic search profile without ever being included in a search result. As such, there are many exterior opportunities to be had beyond the traditional off-site SEO.

Keyword Targeting/Phrase Strategies – building on the above concepts of a relevance train, building out from your core terms will be important as far as understanding search behaviour. The long tail as we know it would be targeted towards potential query refinements n a given subset of searcher types. Building out logical phrase extensions and potential query refinements would be something to look at. Furthermore, with fluxuating ‘personalized ranks’ we would measure SEO success in actual traffic and conversions which puts term targeting into a new light as far as nailing money terms and having a cohesive plan that targets query refinement long-tail opportunities.

Quality Content – this has always been the mantra of many and it continues to carry weight. In considering the value of a web page or a site, user interaction becomes a consideration as far as bounce rates, time spent on page and scrolling activities are concerned. Producing compelling and resourceful content would be at a premium to best leverage these tendencies of the system. If a searcher has selected and interacted with your site on multiple occasions your site would be given weight in their personal rankings as well as related topical and searcher types. The more effective a resource the greater the ranking weight increase.

Search Result Conversion – Those skilled in the art of crafting compelling TITLEs and Snippets will have a leg up as they would likely have higher conversion rates when appearing in a set of results. A search result listing that ‘converts’ better than others in a topical/user space would be given greater importance. Working with the page ‘TITLE’, ‘Meta-Description’ and snippets takes on a more important role in your SEO efforts when adjusting for personalized search. I dare say using analytics and a form of split testing would be a great advantage as far as satisfying what not only ranks, but converts.

Freshness – another area I feel may be important is document freshness in that people could be able to set default date ranges or the system could passively begin to see a pattern of a user accessing more current content. You may have had a ‘money page’ that has been ranking for a year that may no longer be getting all the traffic that is has been used to. I would look at updating such pages with fresh information, or creating new related pages and pass the flow via internal links. Depending on the nature of the content (searcher group profile) more current content may be more popular over the larger data set and thus newer content would be weighted more over-all.

Print Page/bookmark me – some aspects of the system can also consider user activity with a page as far as book marking or printing it out. The easiest way to deal with that is making it easier for the end user to do so. Take care though as ‘print pages’ can also lead to duplicate content, be sure to ensure they are not to be indexed. Make is especially easy for peeps to use the Google Bookmark feature :0)

Site Usability – from a search spider or the end user perspective, having logical architecture and a quality end user experience is also at a premium. The actions within the site begin to form the ‘theme’ that becomes its topical benchmark. If similar searcher types embark on similar pathways and related actions (bookmark, print, navigate, and subscribe to RSS) then this will give greater value to those target pages within that community of search types. This also furthers the relevance profile.

Analytics – I see a strong need for the use of analytics in understanding traffic flows both organic and paid, understanding common pathways, bottlenecks, the paths to conversion, and much more. This data will be of immeasurable use in dealing with many of the factors that can affect SEO in a UPM world. I dare say some more reading on behavioural targeting is even in my future :0)



What’s Next?

We are increasingly faced with the challenges presented by a seemingly instable world of search optimization, which in many ways is true. There never were guarantees in the first place though; this is simply another adaptation that is part of the gig. Many of the aspirations of SEO revolve around targeted traffic. The ramifications implied here mean little more than affecting a more targeted campaign that is measured in traffic and conversions in as much as it is by merely ranking for a term. Rankings will be more fluid and attaining value in SEO will be measured by the ability to bring in targeted traffic more than it is today.

And for now we gently coast back, drop anchor and this leg of the journey has ended. We are back in port and the crew has opted for ale over sea water. Beyond this point we’ll be starting to look closer at User Performance Metrics and their potential role in the future of search in general. I know Bill (Slawski) touched on this area once more with analysis of; Method and apparatus for learning a probabilistic generative model for text, which deals with trying to understand words in the context of phrases and concepts much like the phrase based indexing patents. It also leads into probabilistic models for a given search query to define Patent Bending 101concepts, topics and user groups. At some point I am going to dig into that one as well as a few others that relate to these concepts.

While we’re on User Performance Metrics; Bill also recently discussed some other passive and active methods of UPM collection with Desktop Search and Personal Information Management which is based upon Systems and methods for ranking implicit search results and Systems and methods for constructing and using a user profile. These are also worth looking into as far as conceptualizing what factors can affect search rankings outside of traditional thinking. There will be more to come on this topic to be certain :0)

Until next we meet… stay on the trail of the Fire Horse


The Big List of Google Personalized Search resources;

More from Bill Slawski; Personalized PageRank and Personalized Text Scores  - Google and Personalization in Rankings, Google Personalization Methods and Clustering Users for Personalization - Second thoughts on a G-Phone

M'Dog the Mad Hat with; 8 Ways to Optimize For Personalized Search

Search Engine Land; Google Ramps Up Personalized Search - Personalized Search, Google Bookmarks and Link Building - iGoogle Personalized Search and You -

Beanstalk; Personalization and the Death of SEO
Aaron Wall; How to turn off Personalized Search without logging out
SEO Roundtable; Your Search Results are Personalized
Search Engine Watch; Personalized Search Leaves Google Labs (2005)
Greg Linden; Personalized Search Primer And Personalized Search for Movies

From Google –Personally Speaking - Personalized Search and Privacy - Google Puts users in charge -Talk on your personalized Home Page - More of the world in your pocket

Core Patents used during research;

Personalization of WebSearch – 20050071328 – Mar 01 2005

Variable Personalization of Search Engine Results in a Search Engine – 20050216434 - Sept 29 2005

Personalization of placed content ordering in search results – 20050240580 - October 27, 2005

Systems and methods for managing multiple user accounts – 20060224624 - October 5, 2006

Removing documents – 20070043721 - February 22, 2007


Secondary Patents - Moving Parts

Methods and systems for personalized network searching – 20050131866 – June 16 2005

Systems and methods for providing a graphical display of search activity – 20060224938 - October 5, 2006

Systems and methods for providing subscription-based personalization – 20060224615 - October 5, 2006

Systems and methods for analyzing a user's web history – 20060224583 - October 5, 2006

Systems and methods for combining sets of favourites – 20060224608 - October 5, 2006

Systems and methods for modifying search results based on a user's History – 20060224587 - October 5, 2006


Search the Site

SEO Training

Tools of the Trade


On Twitter

Follow me on Twitter

Site Designed by Verve Developments.