|dc.description.abstract||Our aim is to improve web search engines, approaching the searching problem
considering the user, his/her topics of interest and the navigation context. Furthermore,
the clickstream also contains patterns inside. Our system will also
try to predict the next pages that are going to be visited according to the clickstream.
In a personalized search engine, two different users get different results for
the same query, because the system considers the interests of each user separately.
To personalize search, many sources of information can be used: the
bookmarks of the user, his/her geographical location, his navigation history, etc.
Web search engines have, broadly speaking, three basic phases. They are
crawling, indexing and searching. The information available about the users interest
can be considered in some of those three phases, depending on its nature.
Work on search personalization already exists. We will see them in Chapter 3.
In order to solve the problems of ignorance in relation to the user and his
interests, we have developed a system that keeps track of the web pages that
the user visits (his clickstream).
Our system will analyze the clickstream, and will focus the crawling to pages
related to the topics of interest of the user. Furthermore, each time the user
executes a query, the system will consider his/her navigation context, and pages
related to the navigation context will get better scores.
Furthermore, our system also analyzes the clickstream of the user, and retrieves
some navigation patterns from it. Those patterns will be used to give
some navigation tips to the user based on his navigation context.