|
Block-level link analysis - what does it mean
to you?
Microsoft's research lab has released a paper
in which they discuss a new way to rank web sites. The new
method is called "block-level link analysis".
What is block-level analysis?
It's Microsoft attempt to deal with the faults in PageRank
and HITS (Hyperlink Induced Topic Search):
Link Analysis has shown great potential in improving
the performance of web search. PageRank and HITS are two of
the most popular algorithms.
Most of the existing link analysis algorithms treat a
web page as a single node in the web graph. However, in most
cases, a web page contains multiple semantics and hence the
web page might not be considered as the atomic node.
In this paper, the web page is partitioned into blocks
using the vision-based page segmentation algorithm.
By extracting the page-to-block, block-to-page relationships
from link structure and page layout analysis, we can construct
a semantic graph over the WWW such that each node exactly
represents a single semantic topic. This graph can better
describe the semantic structure of the web.
Based on block-level link analysis, we proposed two new
algorithms, Block Level PageRank and Block Level HITS, whose
performances we study extensively using web data.
How does it work?
In short, the new ranking system assumes that all links on
a web page are not equal. The idea is that a web page can
be divided into blocks that have different topics.
The weight and the relevance of a link is determined by its
location within the blocks. By dividing a web page into blocks,
web pages are no longer the smallest unit when doing a web
search.
Does this mean better search engine results?
Will this method deliver better search results than today?
This has yet to be proved. One problem might be that computers
only see the text on a web page and that human surfers see
a combination of pictures and text.
The same web page may look different to a search engines
spider and to a human visitor.
What does this mean to me and my web site?
This new concept is still in the beta phase and not yet official.
While it might improve the way search engines rank web pages,
we still have to see if Microsoft really uses this algorithm
in its new search engine. At the moment, you don't have to
react to this new ranking method.
Today, Google and Yahoo are the most important search engines.
To optimize your web pages for the latest ranking algorithms
of Google, Yahoo and other major search engines, take a look
at the highly recommended software program IBP.
|
