Enhanced Utility in Search Log Publishing of Infrequent Items

Enhanced Utility in Search Log Publishing of Infrequent Items

S. Belinsha (Department of Computer Science and Engineering,VSB Engineering College, Karur, Tamil Nadu, India) and A.P.V. Raghavendra (Department of Computer Science and Engineering,VSB Engineering College, Karur, Tamil Nadu, India)
DOI: 10.4018/ijitwe.2014040104
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Search engines are being widely used by the web users. The search engine companies are concerned to produce best search results. Search logs are the records which records the interactions between the user and the search engine. Various search patterns, user's behaviors can be analyzed from these logs, which will help to enhance the search results. Publishing these search logs to third party for analysis is a privacy issue. Zealous algorithm of filtering the frequent search items in the search log looses its utility in the course of providing privacy. The proposed confess algorithm extends the work by qualifying the infrequent search items in the log which tends to increase the utility of the search log by preserving the privacy. Confess algorithm involves qualifying the infrequent keywords, URL clicks in the search log and publishing it along with the frequent items.
Article Preview

Earlier work involved the release of the logs with replacing the user identity with random numbers (E. Adar, 2007). But this was not promising one because of less privacy concern and is prone to linkage attack (Michaela Gotz, Ashwin Machanavajjnala & Johannes Gehreke, 2012). Linkage attack involves finding the user from the random id, by linking with another database. So privacy is the serious concern here. Also by the keywords formed by the users, the user’s identity can be revealed.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 13: 4 Issues (2018): 1 Released, 3 Forthcoming
Volume 12: 4 Issues (2017)
Volume 11: 4 Issues (2016)
Volume 10: 4 Issues (2015)
Volume 9: 4 Issues (2014)
Volume 8: 4 Issues (2013)
Volume 7: 4 Issues (2012)
Volume 6: 4 Issues (2011)
Volume 5: 4 Issues (2010)
Volume 4: 4 Issues (2009)
Volume 3: 4 Issues (2008)
Volume 2: 4 Issues (2007)
Volume 1: 4 Issues (2006)
View Complete Journal Contents Listing