@inproceedings{bullock2011privacyaware, abstract = {With the increased popularity of Web 2.0 services in the last years data privacy has become a major concern for users. The more personal data users reveal, the more difficult it becomes to control its disclosure in the web. However, for Web 2.0 service providers, the data provided by users is a valuable source for offering effective, personalised data mining services. One major application is the detection of spam in social bookmarking systems: in order to prevent a decrease of content quality, providers need to distinguish spammers and exclude them from the system. They thereby experience a conflict of interests: on the one hand, they need to identify spammers based on the information they collect about users, on the other hand, they need to respect privacy concerns and process as few personal data as possible. It would therefore be of tremendous help for system developers and users to know which personal data are needed for spam detection and which can be ignored. In this paper we address these questions by presenting a data privacy aware feature engineering approach. It consists of the design of features for spam classification which are evaluated according to both, performance and privacy conditions. Experiments using data from the social bookmarking system BibSonomy show that both conditions must not exclude each other.}, acmid = {2024306}, address = {New York, NY, USA}, articleno = {15}, author = {Bullock, Beate Navarro and Lerch, Hana and Ro\ssnagel, Alexander and Hotho, Andreas and Stumme, Gerd}, booktitle = {Proceedings of the 11th International Conference on Knowledge Management and Knowledge Technologies}, doi = {10.1145/2024288.2024306}, interhash = {7a2d6a35c124ea0fe31c962f8f150916}, intrahash = {00a8f31185a34957eb16d500d7d51398}, isbn = {978-1-4503-0732-1}, location = {Graz, Austria}, numpages = {8}, pages = {15:1--15:8}, publisher = {ACM}, series = {i-KNOW '11}, title = {Privacy-aware spam detection in social bookmarking systems}, url = {http://doi.acm.org/10.1145/2024288.2024306}, year = 2011 } @inproceedings{krause2008antisocial, abstract = {The annotation of web sites in social bookmarking systemshas become a popular way to manage and find informationon the web. The community structure of such systems attractsspammers: recent post pages, popular pages or specifictag pages can be manipulated easily. As a result, searchingor tracking recent posts does not deliver quality resultsannotated in the community, but rather unsolicited, oftencommercial, web sites. To retain the benefits of sharingone’s web content, spam-fighting mechanisms that can facethe flexible strategies of spammers need to be developed.}, address = {New York, NY, USA}, author = {Krause, Beate and Schmitz, Christoph and Hotho, Andreas and Stumme, Gerd}, booktitle = {AIRWeb '08: Proceedings of the 4th International Workshop on Adversarial Information Retrieval on the Web}, doi = {10.1145/1451983.1451998}, file = {krause2008antisocial.pdf:krause2008antisocial.pdf:PDF}, groups = {public}, interhash = {a45d40ac7776551301ad9dde5b25357f}, intrahash = {5b6b648fd25c15d594404ae26fcda6b4}, isbn = {978-1-60558-159-0}, location = {Beijing, China}, month = apr, pages = {61--68}, publisher = {ACM}, timestamp = {2010-11-10 15:35:25}, title = {The Anti-Social Tagger - Detecting Spam in Social Bookmarking Systems}, url = {http://airweb.cse.lehigh.edu/2008/submissions/krause_2008_anti_social_tagger.pdf}, username = {dbenz}, year = 2008 } @inproceedings{krause2008anti, address = {New York, NY, USA}, author = {Krause, Beate and Schmitz, Christoph and Hotho, Andreas and Stumme, Gerd}, booktitle = {AIRWeb '08: Proceedings of the 4th international workshop on Adversarial information retrieval on the web}, doi = {http://doi.acm.org/10.1145/1451983.1451998}, interhash = {a45d40ac7776551301ad9dde5b25357f}, intrahash = {93af1487543e0395ee8f7e0413bbcfc1}, isbn = {978-1-60558-159-0}, location = {Beijing, China}, pages = {61--68}, publisher = {ACM}, title = {The anti-social tagger: detecting spam in social bookmarking systems}, vg-wort = {29.6}, year = 2008 } @inproceedings{krause2008anti, abstract = {The annotation of web sites in social bookmarking systems has become a popular way to manage and find information on the web. The community structure of such systems attracts spammers: recent post pages, popular pages or specific tag pages can be manipulated easily. As a result, searching or tracking recent posts does not deliver quality results annotated in the community, but rather unsolicited, often commercial, web sites. To retain the benefits of sharing one’s web content, spam-fighting mechanisms that can face the flexible strategies of spammers need to be developed.}, address = {New York, NY, USA}, author = {Krause, Beate and Schmitz, Christoph and Hotho, Andreas and Stumme, Gerd}, booktitle = {AIRWeb '08: Proceedings of the 4th International Workshop on Adversarial Information Retrieval on the Web}, doi = {10.1145/1451983.1451998}, interhash = {a45d40ac7776551301ad9dde5b25357f}, intrahash = {5b6b648fd25c15d594404ae26fcda6b4}, isbn = {978-1-60558-159-0}, location = {Beijing, China}, month = apr, pages = {61--68}, publisher = {ACM}, title = {The Anti-Social Tagger - Detecting Spam in Social Bookmarking Systems}, url = {http://airweb.cse.lehigh.edu/2008/submissions/krause_2008_anti_social_tagger.pdf}, year = 2008 } @inproceedings{anti2008krause, address = {New York, NY, USA}, author = {Krause, Beate and Schmitz, Christoph and Hotho, Andreas and Stumme, Gerd}, booktitle = {AIRWeb '08: Proceedings of the 4th international workshop on Adversarial information retrieval on the web}, doi = {http://doi.acm.org/10.1145/1451983.1451998}, interhash = {a45d40ac7776551301ad9dde5b25357f}, intrahash = {68effe5d4b9460f9388e7685310f74c2}, isbn = {978-1-60558-159-0}, location = {Beijing, China}, pages = {61--68}, publisher = {ACM}, title = {The Anti-Social Tagger - Detecting Spam in Social Bookmarking Systems}, url = {http://airweb.cse.lehigh.edu/2008/submissions/krause_2008_anti_social_tagger.pdf}, year = 2008 }