Hybrid Usage-Based Ranking Model for Information Retrieval (Web Search Engine)

Abstract: There are plenty of web pages available on the Internet. It is very challenging for Web Search Engines to find precise result up to user�s expectations for his query from those huge numbers of pages. Most of the search results that correspond to a user's query are not relevant to the user browsing behaviour. Lots of the page ranking algorithms are available to calculate the relevancy of the web page such as Weighted PageRank algorithm or Content Based Ranking to provide a good ranked list. But these ranking algorithms might be not enough to provide a good ranked list, so in this paper, we have come up with a Hybrid Usage-Based Ranking Algorithm where page ranking is generated as a combination of user usage (user hits per link) and vector space result for users query. The result helps the users to get the relevant information quickly.

Keywords: Search engine, Information Retrieval (IR), Usage based, Vector space, Visits of Links (VOL).