A semantic association page rank algorithm for web search engines

Abstract

The majority of Semantic Web search engines retrieve information by focusing on the use of concepts and relations restricted to the query provided by the user. By trying to guess the implicit meaning between these concepts and relations, probabilities are calculated to give the pages a score for ranking. In this study, I propose a relation-based page rank algorithm to be used as a Semantic Web search engine. Relevance is measured as the probability of finding the connections made by the user at the time of the query, as well as the information contained in the base knowledge of the Semantic Web environment. By the use of "virtual links" between the concepts in a page, which are obtained from the knowledge base, we can connect concepts and components of a page and increase the probability score for a better ranking. By creating these connections, this study also looks to eliminate the possibility of getting results equal to zero, and to provide a tie-breaker solution when two or more pages obtain the same score.