Posted on August 31, 2010 by Kevin Getch So, I am at the SEOmoz Pro Training Seminar in Seattle, WA and SEOmoz just unleashed a NEW SEO tool. Their “lead scientist” is showing us mathematical equations that reminded me of a mad scientist writing an equation on a chalk board. So, after I picked up the rest of my brain that was not completely mush and stuffed it back in my head, I started to wrap my head around the significance of this new seo tool from SEOmoz. This seo tool is a potential game changer! So, it looks like SEOmoz is trying to change the SEO game by having their lead scientist, Ben Hendrickson, reverse engineer Google’s Algorithm. Now this has and is being attempted everyday, so what makes this new search engine optimization tool different? It works! The initial presentation of how this tool was created was mind numbingly complicated. But as I tested this tool and ran some different tests with simple searches it was amazingly accurate in depicting which site was more effective in targeting a specific keyword. Rand Fishkin, the CEO of SEOmoz said, “Search engines use topic modeling (we think LDA) to help determine content that is highly “relevant” vs. “not relevant” to a query (e.g. When searching “the stones” you want content that uses words like “Mick Jagger” and “concert dates” but not “ruby” or “emerald”). Building a modeling system against a large num of docs (8+ mil), @bhendrickson has created a highly correlated metrics for measuring which gives a relevancy score you can use to judge the quality of your “topic-modeling” efforts in content.” (via 4 seperate posts on Twitter) So, though I didn’t comprehend all of the science behind what Ben created, I understand it is at least in part based on LDA (Latent Dirichlet Allocation). Here is how Wikipedia defines Latent Dirichlet Allocation, “In statistics, latent Dirichlet allocation (LDA) is a generative model that allows sets of observations to be explained by unobserved groups which explain why some parts of the data are similar. For example, if observations are words collected into documents, it posits that each document is a mixture of a small number of topics and that each word’s creation is attributable to one of the document’s topics. LDA was first presented as a graphical model for topic discovery and was developed by David Blei, Andrew Ng, and Michael Jordan in 2002.” If you would like to get really geeky check out this to learn more about the science behind this new tool. So how can we benefit from this new SEO tool? If you can imagine that this tool will give you all of the words that are used on a site as well as a corresponding score for those combination of keywords for a specific search term (or you can enter your own keywords) why couldn’t I go to a competitors site that is ranking #1 for my desired search term and use this tool to extract all of their keywords, add or change keywords to see how it will affect the score and write some compelling copy using these same keywords. If a light bulb just went off, you’ve got it… if not give it some time.