Relevancy Perception vs. Relevancy Score

May 5, 2005 • 2:55 pm | comments (0) by | Filed Under Search Engine & SEO Theory

In the WebProNews article titled What Constitutes Search Engine Relevancy?, Chris Richardson asks "The question is how do you define relevancy? More importantly, how do search engines define relevancy?"

After a great conversation with Dr. E. Garcia, he pointed me to his latest paper Fractals, L-Systems and Semantics and more specifically to this:

"... users and search engines may not agree in the way they see, read or interpret documents. Essentially,
  • users assess document relevancy by visually interpreting -not necessarily in a linear fashion- information displayed.
  • search engines assess document relevancy by interpreting -tag by tag and in a linear fashion- information coded."
The entire point that he is trying to make is that both users and marketers think of relevancy based on perception while search engines see relevancy as a scoring function.

He also mentioned that this has to do with "the ability to discriminate terms that have different meanings in different context" otherwise known as "term disambiguation". To read more on this subject I recommend you read an outstanding paper called "Disambiguation for Text Mining on the Web" by Einat Amitay and her colleagues at IBM. I believe this paragraph is a good summary:

"The Web today contains a treasure trove of information about subjects such as people, companies, organizations, products, etc. that may be of wide interest. A first step toward any Web-based text mining effort would be to collect a significant number of Web mentions of a subject. However, due to the infamous ambiguity of natural language, many subjects have several meanings. This is particularly true for brand names, which often derive their name from the real word. Thus, the challenge becomes not only to find all the subject occurrences, but also to filter out just those that have the desired meaning."

Ultimately, the user does have the last word on what he or she determines to be the right listing to click on. Therefore, I believe that Barry's [Schwartz] project called RustySearch will be an excellent form of sampling measurement of web search relevancy. Hopefully many webmasters, marketers, business owners, journalists, academics, students and of course users will take the test and by contributing to this experiment will help determine the competitiveness of relevancy between the mayor 4 search engines based on perception.

Barry has already posted the Early Results from RustySearch.

Previous story: Language & Domain Name Issues
Ninja Banner
blog comments powered by Disqus