An Efficient Concept-based Mining Model for Deriving User Profiles

Abstract

User profiling forms the basis for search engine personalization applications. Search engines are personalized so that they optimize the retrieval quality of user queries. User profiling done through concept-based mining identifies terms that render conceptual meaning as well as unimportant terms. Both positive and negative preferences from such conceptual terms are used in creating the user profiles and such profiles built based on both the preferences of a user reflect his/her interests at finer details. Based on these accurate and up-to-date user profiles, relationships between users can be mined to perform Collaborative Filtering (CF) thereby allowing users with the same interests to share their profiles. Collaborative filtering filters information about a user based on a collection of user profiles that are already built from the extracted preferences. Users having similar profiles may share similar interests. The concept-based search enhanced by Collaborative Filtering improves the relevancy of search results by making automatic predictions about the interests of a user by collecting similar user profiles. General Terms Information retrieval, Search engine personalization, Web mining