Using Ups Framework in Personalised Web Search

Personalized web search is a very convenient way to improve search results quality by modifying search results for users with individual information needs. However, users are not easily get ready to expose their private preference information to search engines. On the other hand, privacy for individual is different, and it can be compromised if there is a gain or profit to the user in output. Therefore balance must be maintained between search quality and privacy protection in PWS. The UPS framework adaptively creates user profile by queries while respecting user specified privacy requirements. Our runtime generalization goal is striking a balance between two predictive metrics that evaluate the utility of personalization and the privacy risk of exposing the generalized profile. UPS framework consists of two greedy algorithms GreedyDP and GreedyIL, for runtime profile generalization. Here we also have an online prediction mechanism for deciding personalizing a query is beneficial or not.