Hilltop

[Chatmaster]

I am a great supporter of the TrustRank paper. But I noticed something the other day of someone presenting seminars here in SA. He had a great compilation of subjects and clearly knows the industry well. I then saw something I haven't seen for 3 or 4 years. He actually pressents a subject, Hilltop (ftp://ftp.cs.toronto.edu/pub/reports/csri/405/hilltop.html)! I remember Years ago on the forums, we buzzed about this paper and many thought that it was related to the Austin / Florida update. I believe most of us soon realised that the Hilltop algo was just another theory.

However, with the TrustRank algo clearly at play, can Hilltop play a roll in determining the authority of a site? Any opinions?

[Paz]

Hi,

Yeah there was a lot of excitement about that patent application, but I thought the hilltop algorithm was connected with the implementation of latent semantic indexing - you know, mixing keywords with common variations.

There are so many algorithms though, by the time we've figured out what's going on a new one comes along! One thing that doesn't change though - diversity is essential in any seo campaign, especially with backlinks.

Cheers,
Paz.

[Chatmaster]

Yah, ontology and applied semantics forms part of the Hilltop paper and was where the core focus was placed by most SEO's back then as hilltop use these methods in figuring out the relationships between sites, in order to identify the good quality links.

In reading the above mentioned paper I want to highlight this...

Our approach is based on the same assumptions as the other connectivity algorithms, namely that the number and quality of the sources referring to a page are a good measure of the page's quality. The key difference consists in the fact that we are only considering "expert" sources - pages that have been created with the specific purpose of directing people towards resources. In response to a query, we first compute a list of the most relevant experts on the query topic. Then, we identify relevant links within the selected set of experts, and follow them to identify target web pages. The targets are then ranked according to the number and relevance of non-affiliated experts that point to them. Thus, the score of a target page reflects the collective opinion of the best independent experts on the query topic. When such a pool of experts is not available, Hilltop provides no results. Thus, Hilltop is tuned for result accuracy and not query coverage.

Is it possible that Hilltop can infact suport the TrustRank algo perfectly?

[Paz]

Yes,

I see what you mean now; it's definitely hinting at trust rank!

But I'm a bit confused and I'll have to go back through my notes. Did that Hilltop article pre-date the Google patent application? Because if it did the Google patent's invalid isn't it?

I'll definitely have to dig out my old bookmarks and refresh my memory about this one!

Cheers,
Paz.