2007
07.06

Semantic Indexing

Must read user comment: I happened to catch this article because semantic indexing is my business and I have to comment on your confusion.

Paris and Hilton are not association to anything by Google, neither is tiger and woods. Google does not assume anything and it certainly does not “calculate relations” between different words. It finds match in its index.

Read the full comment

Original post below:

Semantic indexing means that search engines try to associate certain terms with concepts when indexing web pages. For example, Paris and Hilton are associated with a woman instead of a city and a hotel, Tiger and Woods are associated with golf.

How can search engines find the relation between words?

For example, Google has billions of web pages in its index. If Google finds that many web pages contain both the word Paris and the word Hilton then Google might assume that these keywords are related. The other words on these pages could give Google a hint that this special word combination is about a woman.

Words that frequently appear very close to each other could get a tighter connection. Google has a lot of algorithms that allow them to calculate the relation between different words.

Read the rest of the article

No Comment.

Add Your Comment