期刊名称：International Journal of Engineering and Computer Science
印刷版ISSN：2319-7242
出版年度：2015
卷号：4
期号：3
页码：10930-10936
出版社：IJECS
摘要：Personalized web search (PWS)[2][9] has demonstrated its effectiveness in improving the quality of varioussearch services on the Internet. However, evidence show that users’ reluctance to disclose their privateinformation during search has become a major barrier for the wide explosion of PWS. We study privacysecurity in PWS applications that model user preferences as hierarchical user profiles. We suggest a PWSstructure called UPS that can adaptively generalize profiles by queries while respecting user specifiedprivacy requirements. Our runtime simplification aims at striking a balance between two predictive metricsthat evaluate the utility of personalization and the privacy risk of exposing the widespread profile. Wepresent two insatiable algorithms, namely Greedy DP and Greedy IL, for runtime generalization. We alsoprovide an online prediction mechanism for deciding whether personalizing a query is valuable. Extensiveexperiments demonstrate the effectiveness of our framework. The new results also reveal that GreedyIL(Greedy Information Limit) significantly outperforms Greedy DP in terms of efficiency.
关键词：Privacy protection; personalized web search;utility; risk; profile
