What is semantic indexing?

[Ronald Marva]

With several advances in search engine algorithms, there is a growing demand to create a website that has been optimized for many different but related search terms. Here enters the concept of Semantic indexing which means that search engines starts associate certain terms with concepts when indexing web pages.

To cite an example, Black and Christmas are associated with a movie instead of a color and a holiday.

Search engines algorithms now try to find the relation between words. If a number of web pages contain both Black and Christmas, the system will recognize that these keywords are related. This would then lead to a logical process wherein these combine words would be recognized as movie. Google, for one, has a lot of algorithms that allow them to calculate the relation between different words.

With this knowledge on semantic indexing, one is able to recognize that it is important to establishing links to your website which come from topically related pages. This way, search engines would put your website in the right context.

[marketraise2007]

Latent semantic analysis (LSA) is a technique in natural language processing, in particular in vectorial semantics, of analyzing relationships between a set of documents and the terms they contain by producing a set of concepts related to the documents and terms.LSA uses a term-document matrix which describes the occurrences of terms in documents; it is a sparse matrix whose rows correspond to terms and whose columns correspond to documents , typically stemmed words that appear in the documents.This matrix is also common to standard semantic models, though it is not necessarily explicitly expressed as a matrix, since the mathematical properties of matrix are not always used.LsA is basically used for the following purposes
1)Compare the documents in the concept space 2)Find similar documents across languages, after analyzing a base set of translated documents 3)Find relations between terms 4)Given a query of terms, translate it into the concept space, and find matching documents.After the construction of the occurrence matrix, LSA finds a low-rank approximation to the term-document matrix. The consequence of the rank lowering is that some dimensions are combined and depend on more than one term.LSA has two drawbacks:a)The resulting dimensions might be difficult to interpret b)The probabilistic model of LSA does not match observed data.It is implemented by typically computed using large matrix methods but may also be computed incrementally and with greatly reduced resources via a neural network-like approach which does not require the large, full-rank matrix to be held in memory.

[imroanne]

Example of LSI or Semantic Indexing:

Latent Semantic Indexing is like allowing these 1 keyword be defined into various categories, whichever is approriate for such site.

Ex: Windows

Windows can be defined simply as a part of the house.
But also can be defined as an Operating system.


Hence, google will suggest various terms synanimous to the word windows to better target your search.

Other results are segregated according to its categorized conotation/denotation. try searching for dub.

[Ronald Marva]

Originally Posted by marketraise2007

LSA uses a term-document matrix which describes the occurrences of terms in documents; it is a sparse matrix whose rows correspond to terms and whose columns correspond to documents , typically stemmed words that appear in the documents.

This term-document matrix is precisely what I mean when patterns in unstructured data are collated and its correlation analyzed; then those patterns are used to offer more effective search and categorization services.

This underlines the importance of understanding semantics indexing for SEO professionals who want to have a more meaning success in their campaigns.