Abstract

A personalized search engine that captures the users preferences in the form of concepts by mining their click through data. Due to the value of location information in search, in this technique the user preferences are organized in an ontology-based, versatile user profile, which are used to adapt a personalized ranking function for rank adaptation of future search results. Based on the client-server model, presented is a detailed architecture and design for implementation of Personalized Search Engine. In design, the client collects and stores locally the click through data to protect privacy, whereas important tasks such as concept mining training, and re-ranking are performed at the Personalized Search Engine server. Moreover, the privacy issue is addressed by restricting the information in the user profile exposed to the server. This technique of Personalized Search Engine is prototyped on the Google Android platform.

Authors and Affiliations