A hybrid re-ranking algorithm based on ontological user profiles

The rapid expansion of the Internet has caused information overload to such an extent that the process of finding a specific piece of information may often become frustrating and time-consuming for users. In this paper, we present a hybrid personalized search model based on learning ontological user profiles implicitly. The main goal of this paper is to capture interesting and uninteresting web pages from user browsing behaviour. These web pages are stored in user profile under positive and negative documents. We propose a hybrid re-ranking algorithm that is based on the combination of different information resources collected from the reference ontology, user profile and original search engine's ranking. Experiments show that our model offers improved performance over the Google search engine.