CrowdLogging: Distributed, Private, and Anonymous Search Logging. Feild, H., Allan, J., & Glatt, J. In Proceedings of the 34th international ACM SIGIR Conference on Research and development in Information Retrieval (SIGIR 2011), pages 375–384, 2011. ACM. Issue: 2doi abstract bibtex We describe CrowdLogging, an approach for distributed search log collection, storage, and mining, with the dual goals of preserving privacy and making the mined informa- tion broadly available. Most search log mining approaches and most privacy enhancing schemes have focused on cen- tralized search logs and methods for disseminating them to third parties. In our approach, a user’s search log is en- crypted and shared in such a way that (a) the source of a search behavior artifact, such as a query, is unknown and (b) extremely rare artifacts—that is, artifacts more likely to contain private information—are not revealed. The ap- proach works with any search behavior artifact that can be extracted from a search log, including queries, query reformulations, and query-click pairs. In this work, we: (1) present a distributed search log collection, storage, and mining framework; (2) compare several privacy policies, including differential privacy, showing the trade-offs between strong guarantees and the utility of the released data; (3) demonstrate the impact of our approach using two existing research query logs; and (4) describe a pilot study for which we implemented a version of the framework.
@inproceedings{feild_crowdlogging_2011,
title = {{CrowdLogging}: {Distributed}, {Private}, and {Anonymous} {Search} {Logging}},
isbn = {978-1-4503-0757-4},
doi = {http://doi.acm.org/10.1145/2009916.2009969},
abstract = {We describe CrowdLogging, an approach for distributed search log collection, storage, and mining, with the dual goals of preserving privacy and making the mined informa- tion broadly available. Most search log mining approaches and most privacy enhancing schemes have focused on cen- tralized search logs and methods for disseminating them to third parties. In our approach, a user’s search log is en- crypted and shared in such a way that (a) the source of a search behavior artifact, such as a query, is unknown and (b) extremely rare artifacts—that is, artifacts more likely to contain private information—are not revealed. The ap- proach works with any search behavior artifact that can be extracted from a search log, including queries, query reformulations, and query-click pairs. In this work, we: (1) present a distributed search log collection, storage, and mining framework; (2) compare several privacy policies, including differential privacy, showing the trade-offs between strong guarantees and the utility of the released data; (3) demonstrate the impact of our approach using two existing research query logs; and (4) describe a pilot study for which we implemented a version of the framework.},
booktitle = {Proceedings of the 34th international {ACM} {SIGIR} {Conference} on {Research} and development in {Information} {Retrieval} ({SIGIR} 2011)},
publisher = {ACM},
author = {Feild, Henry and Allan, James and Glatt, Joshua},
year = {2011},
note = {Issue: 2},
keywords = {CrowdLogging, Distributed query logs, crowdlogging, log analysis, logfiles, private query log analysis, query logs, web logs: query logs},
pages = {375--384},
}
Downloads: 0
{"_id":"mMCSnypMSBPHWGs9t","bibbaseid":"feild-allan-glatt-crowdloggingdistributedprivateandanonymoussearchlogging-2011","author_short":["Feild, H.","Allan, J.","Glatt, J."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"CrowdLogging: Distributed, Private, and Anonymous Search Logging","isbn":"978-1-4503-0757-4","doi":"http://doi.acm.org/10.1145/2009916.2009969","abstract":"We describe CrowdLogging, an approach for distributed search log collection, storage, and mining, with the dual goals of preserving privacy and making the mined informa- tion broadly available. Most search log mining approaches and most privacy enhancing schemes have focused on cen- tralized search logs and methods for disseminating them to third parties. In our approach, a user’s search log is en- crypted and shared in such a way that (a) the source of a search behavior artifact, such as a query, is unknown and (b) extremely rare artifacts—that is, artifacts more likely to contain private information—are not revealed. The ap- proach works with any search behavior artifact that can be extracted from a search log, including queries, query reformulations, and query-click pairs. In this work, we: (1) present a distributed search log collection, storage, and mining framework; (2) compare several privacy policies, including differential privacy, showing the trade-offs between strong guarantees and the utility of the released data; (3) demonstrate the impact of our approach using two existing research query logs; and (4) describe a pilot study for which we implemented a version of the framework.","booktitle":"Proceedings of the 34th international ACM SIGIR Conference on Research and development in Information Retrieval (SIGIR 2011)","publisher":"ACM","author":[{"propositions":[],"lastnames":["Feild"],"firstnames":["Henry"],"suffixes":[]},{"propositions":[],"lastnames":["Allan"],"firstnames":["James"],"suffixes":[]},{"propositions":[],"lastnames":["Glatt"],"firstnames":["Joshua"],"suffixes":[]}],"year":"2011","note":"Issue: 2","keywords":"CrowdLogging, Distributed query logs, crowdlogging, log analysis, logfiles, private query log analysis, query logs, web logs: query logs","pages":"375–384","bibtex":"@inproceedings{feild_crowdlogging_2011,\n\ttitle = {{CrowdLogging}: {Distributed}, {Private}, and {Anonymous} {Search} {Logging}},\n\tisbn = {978-1-4503-0757-4},\n\tdoi = {http://doi.acm.org/10.1145/2009916.2009969},\n\tabstract = {We describe CrowdLogging, an approach for distributed search log collection, storage, and mining, with the dual goals of preserving privacy and making the mined informa- tion broadly available. Most search log mining approaches and most privacy enhancing schemes have focused on cen- tralized search logs and methods for disseminating them to third parties. In our approach, a user’s search log is en- crypted and shared in such a way that (a) the source of a search behavior artifact, such as a query, is unknown and (b) extremely rare artifacts—that is, artifacts more likely to contain private information—are not revealed. The ap- proach works with any search behavior artifact that can be extracted from a search log, including queries, query reformulations, and query-click pairs. In this work, we: (1) present a distributed search log collection, storage, and mining framework; (2) compare several privacy policies, including differential privacy, showing the trade-offs between strong guarantees and the utility of the released data; (3) demonstrate the impact of our approach using two existing research query logs; and (4) describe a pilot study for which we implemented a version of the framework.},\n\tbooktitle = {Proceedings of the 34th international {ACM} {SIGIR} {Conference} on {Research} and development in {Information} {Retrieval} ({SIGIR} 2011)},\n\tpublisher = {ACM},\n\tauthor = {Feild, Henry and Allan, James and Glatt, Joshua},\n\tyear = {2011},\n\tnote = {Issue: 2},\n\tkeywords = {CrowdLogging, Distributed query logs, crowdlogging, log analysis, logfiles, private query log analysis, query logs, web logs: query logs},\n\tpages = {375--384},\n}\n\n","author_short":["Feild, H.","Allan, J.","Glatt, J."],"key":"feild_crowdlogging_2011","id":"feild_crowdlogging_2011","bibbaseid":"feild-allan-glatt-crowdloggingdistributedprivateandanonymoussearchlogging-2011","role":"author","urls":{},"keyword":["CrowdLogging","Distributed query logs","crowdlogging","log analysis","logfiles","private query log analysis","query logs","web logs: query logs"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/ifromm","dataSources":["N4kJAiLiJ7kxfNsoh"],"keywords":["crowdlogging","distributed query logs","crowdlogging","log analysis","logfiles","private query log analysis","query logs","web logs: query logs"],"search_terms":["crowdlogging","distributed","private","anonymous","search","logging","feild","allan","glatt"],"title":"CrowdLogging: Distributed, Private, and Anonymous Search Logging","year":2011}