@inproceedings{krause2008antisocial, 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. A classical approach in machine learning is to determine relevant features that describe the system's users, train different classifiers with the selected features and choose the one with the most promising evaluation results. In this paper we will transfer this approach to a social bookmarking setting to identify spammers. We will present features considering the topological, semantic and profile-based information which people make public when using the system. The dataset used is a snapshot of the social bookmarking system BibSonomy and was built over the course of several months when cleaning the system from spam. Based on our features, we will learn a large set of different classification models and compare their performance. Our results represent the groundwork for a first application in BibSonomy and for the building of more elaborate spam detection mechanisms.}, acmid = {1451998}, address = {New York, NY, USA}, author = {Krause, Beate and Schmitz, Christoph and Hotho, Andreas and Stumme, Gerd}, booktitle = {Proceedings of the 4th International Workshop on Adversarial Information Retrieval on the Web}, doi = {10.1145/1451983.1451998}, interhash = {a45d40ac7776551301ad9dde5b25357f}, intrahash = {50c22098a7a85b1e43e7e4df1d8a3e7a}, isbn = {978-1-60558-159-0}, location = {Beijing, China}, numpages = {8}, pages = {61--68}, publisher = {ACM}, series = {AIRWeb '08}, title = {The Anti-social Tagger: Detecting Spam in Social Bookmarking Systems}, url = {http://doi.acm.org/10.1145/1451983.1451998}, year = 2008 } @article{Benz:2010:SBP:1921763.1921804, abstract = {Social resource sharing systems are central elements of the Web 2.0 and use the same kind of lightweight knowledge representation, called folksonomy. Their large user communities and ever-growing networks of user-generated content have made them an attractive object of investigation for researchers from different disciplines like Social Network Analysis, Data Mining, Information Retrieval or Knowledge Discovery. In this paper, we summarize and extend our work on different aspects of this branch of Web 2.0 research, demonstrated and evaluated within our own social bookmark and publication sharing system BibSonomy, which is currently among the three most popular systems of its kind. We structure this presentation along the different interaction phases of a user with our system, coupling the relevant research questions of each phase with the corresponding implementation issues. This approach reveals in a systematic fashion important aspects and results of the broad bandwidth of folksonomy research like capturing of emergent semantics, spam detection, ranking algorithms, analogies to search engine log data, personalized tag recommendations and information extraction techniques. We conclude that when integrating a real-life application like BibSonomy into research, certain constraints have to be considered; but in general, the tight interplay between our scientific work and the running system has made BibSonomy a valuable platform for demonstrating and evaluating Web 2.0 research.}, acmid = {1921804}, address = {Secaucus, NJ, USA}, author = {Benz, Dominik and Hotho, Andreas and J\"{a}schke, Robert and Krause, Beate and Mitzlaff, Folke and Schmitz, Christoph and Stumme, Gerd}, doi = {10.1007/s00778-010-0208-4}, interhash = {e65eac84a375ab707492051fadc77db2}, intrahash = {cf9f0462a31f4816126046133bb497e1}, issn = {1066-8888}, issue_date = {December 2010}, journal = {The VLDB Journal}, month = dec, number = 6, numpages = {27}, pages = {849--875}, publisher = {Springer-Verlag New York, Inc.}, title = {The Social Bookmark and Publication Management System Bibsonomy}, url = {http://dx.doi.org/10.1007/s00778-010-0208-4}, volume = 19, year = 2010 } @article{benz2010social, abstract = {Social resource sharing systems are central elements of the Web 2.0 and use the same kind of lightweight knowledge representation, called folksonomy. Their large user communities and ever-growing networks of user-generated content have made them an attractive object of investigation for researchers from different disciplines like Social Network Analysis, Data Mining, Information Retrieval or Knowledge Discovery. In this paper, we summarize and extend our work on different aspects of this branch of Web 2.0 research, demonstrated and evaluated within our own social bookmark and publication sharing system BibSonomy, which is currently among the three most popular systems of its kind. We structure this presentation along the different interaction phases of a user with our system, coupling the relevant research questions of each phase with the corresponding implementation issues. This approach reveals in a systematic fashion important aspects and results of the broad bandwidth of folksonomy research like capturing of emergent semantics, spam detection, ranking algorithms, analogies to search engine log data, personalized tag recommendations and information extraction techniques. We conclude that when integrating a real-life application like BibSonomy into research, certain constraints have to be considered; but in general, the tight interplay between our scientific work and the running system has made BibSonomy a valuable platform for demonstrating and evaluating Web 2.0 research.}, acmid = {1921804}, address = {Secaucus, NJ, USA}, author = {Benz, Dominik and Hotho, Andreas and J\"{a}schke, Robert and Krause, Beate and Mitzlaff, Folke and Schmitz, Christoph and Stumme, Gerd}, doi = {10.1007/s00778-010-0208-4}, interhash = {e65eac84a375ab707492051fadc77db2}, intrahash = {cf9f0462a31f4816126046133bb497e1}, issn = {1066-8888}, issue_date = {December 2010}, journal = {The VLDB Journal}, month = dec, number = 6, numpages = {27}, pages = {849--875}, publisher = {Springer-Verlag New York, Inc.}, title = {The Social Bookmark and Publication Management System Bibsonomy}, url = {http://dx.doi.org/10.1007/s00778-010-0208-4}, volume = 19, year = 2010 } @article{benz2010social, abstract = {Social resource sharing systems are central elements of the Web 2.0 and use the same kind of lightweight knowledge representation, called folksonomy. Their large user communities and ever-growing networks of user-generated content have made them an attractive object of investigation for researchers from different disciplines like Social Network Analysis, Data Mining, Information Retrieval or Knowledge Discovery. In this paper, we summarize and extend our work on different aspects of this branch of Web 2.0 research, demonstrated and evaluated within our own social bookmark and publication sharing system BibSonomy, which is currently among the three most popular systems of its kind. We structure this presentation along the different interaction phases of a user with our system, coupling the relevant research questions of each phase with the corresponding implementation issues. This approach reveals in a systematic fashion important aspects and results of the broad bandwidth of folksonomy research like capturing of emergent semantics, spam detection, ranking algorithms, analogies to search engine log data, personalized tag recommendations and information extraction techniques. We conclude that when integrating a real-life application like BibSonomy into research, certain constraints have to be considered; but in general, the tight interplay between our scientific work and the running system has made BibSonomy a valuable platform for demonstrating and evaluating Web 2.0 research.}, acmid = {1921804}, address = {Secaucus, NJ, USA}, author = {Benz, Dominik and Hotho, Andreas and J\"{a}schke, Robert and Krause, Beate and Mitzlaff, Folke and Schmitz, Christoph and Stumme, Gerd}, doi = {10.1007/s00778-010-0208-4}, interhash = {e65eac84a375ab707492051fadc77db2}, intrahash = {cf9f0462a31f4816126046133bb497e1}, issn = {1066-8888}, issue_date = {December 2010}, journal = {The VLDB Journal}, month = dec, number = 6, numpages = {27}, pages = {849--875}, privnote = {Cooles Tool dieses PUMA.}, publisher = {Springer-Verlag New York, Inc.}, title = {The Social Bookmark and Publication Management System Bibsonomy}, url = {http://dx.doi.org/10.1007/s00778-010-0208-4}, volume = 19, year = 2010 } @article{benz2010social, abstract = {Social resource sharing systems are central elements of the Web 2.0 and use the same kind of lightweight knowledge representation, called folksonomy. Their large user communities and ever-growing networks of user-generated content have made them an attractive object of investigation for researchers from different disciplines like Social Network Analysis, Data Mining, Information Retrieval or Knowledge Discovery. In this paper, we summarize and extend our work on different aspects of this branch of Web 2.0 research, demonstrated and evaluated within our own social bookmark and publication sharing system BibSonomy, which is currently among the three most popular systems of its kind. We structure this presentation along the different interaction phases of a user with our system, coupling the relevant research questions of each phase with the corresponding implementation issues. This approach reveals in a systematic fashion important aspects and results of the broad bandwidth of folksonomy research like capturing of emergent semantics, spam detection, ranking algorithms, analogies to search engine log data, personalized tag recommendations and information extraction techniques. We conclude that when integrating a real-life application like BibSonomy into research, certain constraints have to be considered; but in general, the tight interplay between our scientific work and the running system has made BibSonomy a valuable platform for demonstrating and evaluating Web 2.0 research.}, address = {Berlin / Heidelberg}, author = {Benz, Dominik and Hotho, Andreas and Jäschke, Robert and Krause, Beate and Mitzlaff, Folke and Schmitz, Christoph and Stumme, Gerd}, doi = {10.1007/s00778-010-0208-4}, interhash = {57fe43734b18909a24bf5bf6608d2a09}, intrahash = {c9437d5ec56ba949f533aeec00f571e3}, issn = {1066-8888}, journal = {The VLDB Journal}, month = dec, number = 6, pages = {849--875}, publisher = {Springer}, title = {The Social Bookmark and Publication Management System BibSonomy}, url = {http://www.kde.cs.uni-kassel.de/pub/pdf/benz2010social.pdf}, volume = 19, year = 2010 } @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}, 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{hotho2006trend, abstract = {As the number of resources on the web exceeds by far the number of documents one can track, it becomes increasingly difficult to remain up to date on ones own areas of interest. The problem becomes more severe with the increasing fraction of multimedia data, from which it is difficult to extract some conceptual description of their contents.

One way to overcome this problem are social bookmark tools, which are rapidly emerging on the web. In such systems, users are setting up lightweight conceptual structures called folksonomies, and overcome thus the knowledge acquisition bottleneck. As more and more people participate in the effort, the use of a common vocabulary becomes more and more stable. We present an approach for discovering topic-specific trends within folksonomies. It is based on a differential adaptation of the PageRank algorithm to the triadic hypergraph structure of a folksonomy. The approach allows for any kind of data, as it does not rely on the internal structure of the documents. In particular, this allows to consider different data types in the same analysis step. We run experiments on a large-scale real-world snapshot of a social bookmarking system.}, acmid = {2080225}, address = {Berlin, Heidelberg}, author = {Hotho, Andreas and J\"{a}schke, Robert and Schmitz, Christoph and Stumme, Gerd}, booktitle = {Proceedings of the First international conference on Semantic and Digital Media Technologies}, doi = {10.1007/11930334_5}, interhash = {33e9a7059f7063a9f5fa40dccf95e7c9}, intrahash = {d13084c0e42631a37611cef045ce6864}, isbn = {3-540-49335-2, 978-3-540-49335-8}, location = {Athens, Greece}, numpages = {15}, pages = {56--70}, publisher = {Springer-Verlag}, series = {SAMT'06}, title = {Trend detection in folksonomies}, url = {http://dx.doi.org/10.1007/11930334_5}, year = 2006 } @article{hotho2010publikationsmanagement, abstract = {Kooperative Verschlagwortungs- bzw. Social-Bookmarking-Systeme wie Delicious, Mister Wong oder auch unser eigenes System BibSonomy erfreuen sich immer größerer Beliebtheit und bilden einen zentralen Bestandteil des heutigen Web 2.0. In solchen Systemen erstellen Nutzer leichtgewichtige Begriffssysteme, sogenannte Folksonomies, die die Nutzerdaten strukturieren. Die einfache Bedienbarkeit, die Allgegenwärtigkeit, die ständige Verfügbarkeit, aber auch die Möglichkeit, Gleichgesinnte spontan in solchen Systemen zu entdecken oder sie schlicht als Informationsquelle zu nutzen, sind Gründe für ihren gegenwärtigen Erfolg. Der Artikel führt den Begriff Social Bookmarking ein und diskutiert zentrale Elemente wie Browsing und Suche am Beispiel von BibSonomy anhand typischer Arbeitsabläufe eines Wissenschaftlers. Wir beschreiben die Architektur von BibSonomy sowie Wege der Integration und Vernetzung von BibSonomy mit Content-Management-Systemen und Webauftritten. Der Artikel schließt mit Querbezügen zu aktuellen Forschungsfragen im Bereich Social Bookmarking.}, author = {Hotho, Andreas and Benz, Dominik and Eisterlehner, Folke and Jäschke, Robert and Krause, Beate and Schmitz, Christoph and Stumme, Gerd}, editor = {Hengartner, Urs and Meier, Andreas}, interhash = {c19880489182c86e1573a2ac983c7cff}, intrahash = {422096948d4de38a725b428be3222d60}, issn = {1436-3011}, journal = {HMD - Praxis der Wirtschaftsinformatik}, month = feb, pages = {47--58}, publisher = {dpunkt.verlag}, title = {Publikationsmanagement mit BibSonomy - ein Social-Bookmarking-System für Wissenschaftler}, url = {http://hmd.dpunkt.de/271/05.php}, volume = 271, year = 2010 } @inproceedings{schmitz2006content, abstract = {Recently, research projects such as PADLR and SWAP have developed tools like Edutella or Bibster, which are targeted at establishing peer-to-peer knowledge management (P2PKM) systems. In such a system, it is necessary to obtain provide brief semantic descriptions of peers, so that routing algorithms or matchmaking processes can make decisions about which communities peers should belong to, or to which peers a given query should be forwarded. This paper provides a graph clustering technique on knowledge bases for that purpose. Using this clustering, we can show that our strategy requires up to 58% fewer queries than the baselines to yield full recall in a bibliographic P2PKM scenario.}, address = {Heidelberg}, author = {Schmitz, Christoph and Hotho, Andreas and Jäschke, Robert and Stumme, Gerd}, booktitle = {The Semantic Web: Research and Applications}, editor = {Sure, York and Domingue, John}, interhash = {d2ddbb8f90cd271dc18670e4c940ccfb}, intrahash = {1788c88e04112a4491f19dfffb8dc39e}, pages = {530-544}, publisher = {Springer}, series = {LNAI}, title = {Content Aggregation on Knowledge Bases using Graph Clustering}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2006/schmitz2006content.pdf}, volume = 4011, year = 2006 } @inproceedings{tane04semantic, author = {Tane, Julien and Schmitz, Christoph and Stumme, Gerd}, bibsource = {DBLP, http://dblp.uni-trier.de}, booktitle = {Proc. 13th International World Wide Web Conference (WWW 2004)}, ee = {http://doi.acm.org/10.1145/1013369}, interhash = {92089bd1e3e798b50fe7c82cd8333e7b}, intrahash = {10efb9940c6f2881cd6c84b6c52bebd8}, pages = {1-10}, title = {Semantic resource management for the web: an e-learning application}, url = {http://www.www2004.org/proceedings/docs/2p1.pdf}, year = 2004 }