An Automatic User Interest Mining Technique for Retrieving Quality Data

Abstract

Search engines acts as an intermediate between the user and web. It takes the user query as input and retrieves the pages based on query terms from its database, which is in advance populated from World Wide Web. It then applies some ranking algorithm to sort the retrieved pages and presents the results back to the user in the form of millions of web pages. But most of pages in the result are not useful to the user. This problem arises because the search engine retrieves the results based on query keywords only and no attention is paid in incorporating the user interest during the ranking process. Due to the lack of automatic mechanism for tracking user browsing patterns, user seldom gets the relevant results in the top ten links. So, in order to cater the need of individual user, an automatic user interest mining technique for retrieving quality data is being proposed here. The mechanism provides the satisfactory results to the user as each user interest is maintained separately without any hassle at the user end.