WEB MINING Link Analysis Search Engines User's Web Behavior HITS
Algorithm Fuzzy Cognitive Map Radial Basis Function PageRank Algorithm
Interior Point Method Fuzzy Bags Rgeression Models Rough Sets
Information Theory Thisbookpresentsaspeci?cand uni?ed approach framework
to three- jor components: Search Engines Performance, Link Analysis, and
User's Web Behavior.
TheexplosivegrowthandthewidespreadaccessibilityoftheWWW has led to a
surge of research activity in the area of information retrieval on VI
Preface the WWW. The three aspects of web mining follow the taxonomy of
the above diagram: Link Analysis, Search engines, and User's web
behavior are considered in the unifying approach. The book is organized
in three sections as follows: 1. In section I of the book (chapters 2-4)
we study Link Analysis within the hubs and authorities framework. Link
Analysis is the science of hyperlink structures ranking, which are used
to determine the relative authority of a Web page and produce improved
algorithms for the ranking of Web search results. We use the HITS
Algorithm developed by Kleinberg and we propose to study HITS in a 2-D
new space: In-degree and Out Degree variables. After we categorize each
web page into a speci?c toplogy we study the impact of each web topology
on HITS in the new 2-D space. We describe why HITS does not fare well in
almost all the di?erent topologies of web graphs. We also describe the
PageRank Algorithm in this new 2-D space.
