@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 } @article{jaeschke2008tag, abstract = {Collaborative tagging systems allow users to assign keywords - so called "tags" - to resources. Tags are used for navigation, finding resources and serendipitous browsing and thus provide an immediate benefit for users. These systems usually include tag recommendation mechanisms easing the process of finding good tags for a resource, but also consolidating the tag vocabulary across users. In practice, however, only very basic recommendation strategies are applied. In this paper we evaluate and compare several recommendation algorithms on large-scale real life datasets: an adaptation of user-based collaborative filtering, a graph-based recommender built on top of the FolkRank algorithm, and simple methods based on counting tag occurences. We show that both FolkRank and Collaborative Filtering provide better results than non-personalized baseline methods. Moreover, since methods based on counting tag occurrences are computationally cheap, and thus usually preferable for real time scenarios, we discuss simple approaches for improving the performance of such methods. We show, how a simple recommender based on counting tags from users and resources can perform almost as good as the best recommender. }, address = {Amsterdam}, author = {Jäschke, Robert and Marinho, Leandro and Hotho, Andreas and Schmidt-Thieme, Lars and Stumme, Gerd}, doi = {10.3233/AIC-2008-0438}, editor = {Giunchiglia, Enrico}, interhash = {b2f1aba6829affc85d852ea93a8e39f7}, intrahash = {955bcf14f3272ba6eaf3dadbef6c0b10}, issn = {0921-7126}, journal = {AI Communications}, number = 4, pages = {231-247}, publisher = {IOS Press}, title = {Tag Recommendations in Social Bookmarking Systems}, url = {http://dx.doi.org/10.3233/AIC-2008-0438}, vgwort = {63}, volume = 21, year = 2008 } @inproceedings{krause2008logsonomy, abstract = {Social bookmarking systems constitute an established part of the Web 2.0. In such systems users describe bookmarks by keywords called tags. The structure behind these social systems, called folksonomies, can be viewed as a tripartite hypergraph of user, tag and resource nodes. This underlying network shows specific structural properties that explain its growth and the possibility of serendipitous exploration. Today’s search engines represent the gateway to retrieve information from the World Wide Web. Short queries typically consisting of two to three words describe a user’s information need. In response to the displayed results of the search engine, users click on the links of the result page as they expect the answer to be of relevance. This clickdata can be represented as a folksonomy in which queries are descriptions of clicked URLs. The resulting network structure, which we will term logsonomy is very similar to the one of folksonomies. In order to find out about its properties, we analyze the topological characteristics of the tripartite hypergraph of queries, users and bookmarks on a large snapshot of del.icio.us and on query logs of two large search engines. All of the three datasets show small world properties. The tagging behavior of users, which is explained by preferential attachment of the tags in social bookmark systems, is reflected in the distribution of single query words in search engines. We can conclude that the clicking behaviour of search engine users based on the displayed search results and the tagging behaviour of social bookmarking users is driven by similar dynamics.}, address = {New York, NY, USA}, author = {Krause, Beate and Jäschke, Robert and Hotho, Andreas and Stumme, Gerd}, booktitle = {HT '08: Proceedings of the Nineteenth ACM Conference on Hypertext and Hypermedia}, doi = {http://doi.acm.org/10.1145/1379092.1379123}, interhash = {6d34ea1823d95b9dbf37d4db4d125d2a}, intrahash = {e64d14f3207766f4afc65983fa759ffe}, isbn = {978-1-59593-985-2}, location = {Pittsburgh, PA, USA}, pages = {157--166}, publisher = {ACM}, title = {Logsonomy - Social Information Retrieval with Logdata}, url = {http://portal.acm.org/citation.cfm?id=1379092.1379123&coll=ACM&dl=ACM&type=series&idx=SERIES399&part=series&WantType=Journals&title=Proceedings%20of%20the%20nineteenth%20ACM%20conference%20on%20Hypertext%20and%20hypermedia}, vgwort = {17}, year = 2008 }