An Effective Personalized Search Engine Architecture for Re-ranking Search Results Using User Behavior

An Effective Personalized Search Engine Architecture for Re-ranking Search Results Using User Behavior Web search engines provide users with a Large number of results for a submitted query. However, not all return results are relevant to the uses needs. In this paper, we proposed a new web search personalization approach that captures the user's interest and references in the form of concepts by mining search results and they click through. In this paper an effective mixture personalized reranking search approach is proposed by modeling user's search wellbeing in a conceptual user profile and then exploiting this profile in the re-ranking process. In this each concept in the user profile consist of two types of documents: categorization document and viewed document Taxonomy is used to represent the user general interest as it contains information from web pages originally associated with open dictionary project category. Viewed documents are used to represent the user's specific interest as it contains information from the web pages clicked by the users. Finally the system create a semantic profile of the user's by monitor and analyze the user's search history. The search results generated will utilize and incorporation of various techniques including clustering, re-ranking and semantic user profile to enhance the performance of the web search engine