Research On Personalized Query Expansion Techniques Based On Social Bookmarks

Personalized search are highly demanded along with the explosion of information on Internet. Because of the diversity of users' interests and behavior, it is a great challenge to provide appropriate search results for different users.First in this paper, the existing personalized information retrieval of search engine and query expansion techniques are classified, and we analyzed their advantage and disadvantage. Then a new Personalized Query Expansion approach based on Social Bookmarks is proposed. This method proposes that refine user's initial query through social bookmarks and page of social bookmarks of user.The main research is through user's data of delicious which is a wab site, four kinds of new personality query expansion algorithm based on social bookmarks: Bookmarks Analysis Extension algorithm,Bookmark Cluster Analysis Extension algorithm,TF Analysis Query Expansion algorithm,Social Bookmarks Query Co-occurrence Analysis extension algorithm. Experimental results show that the proposed Social Bookmarks Query Co-occurrence Analysis extension algorithm is the best.In order to study this four kinds of personality query expansion algorithm,I design and implement a personalized meta search engine query expansion system M_Search_PBM and propose add a layer of the Google personalized query expansion-tier architecture. System provides the user login, the number of expand query words and the four kinds of query expansion algorithm. Finally using a variety of assessment methods and Google search results were compared. Experimental results show that the proposed Social Bookmarks Query Co-occurrence Analysis extension algorithm is better to meet the personalized needs of users, search results than Google's search results more close to user requirements.