@article{Atzmueller:12c, author = {Atzmueller, Martin}, title = {Mining Social Media: Key Players, Sentiments, and Communities}, journal = {WIREs: Data Mining and Knowledge Discovery}, year = {2012}, volume = {In Press}, keywords = {2012, analysis, community, data, detection, itegpub, mining, network, opinion, sentiment, social, venus, vikamine} }

%0 = article %A = Atzmueller, Martin %D = 2012 %T = Mining Social Media: Key Players, Sentiments, and Communities

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.

@inproceedings{bullock2011privacyaware, author = {Bullock, Beate Navarro and Lerch, Hana and Ro Alexander and Hotho, Andreas and Stumme, Gerd}, title = {Privacy-aware spam detection in social bookmarking systems}, booktitle = {Proceedings of the 11th International Conference on Knowledge Management and Knowledge Technologies}, series = {i-KNOW '11}, publisher = {ACM}, address = {New York, NY, USA}, year = {2011}, pages = {15:1--15:8}, url = {http://doi.acm.org/10.1145/2024288.2024306}, doi = {10.1145/2024288.2024306}, isbn = {978-1-4503-0732-1}, keywords = {2011, aware, classification, data-mining, detection, info20, itegpub, myown, social, spam, spam-detection, web2.0, web20}, 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.} }

%0 = inproceedings %A = Bullock, Beate Navarro and Lerch, Hana and Ro Alexander and Hotho, Andreas and Stumme, Gerd %B = Proceedings of the 11th International Conference on Knowledge Management and Knowledge Technologies %C = New York, NY, USA %D = 2011 %I = ACM %T = Privacy-aware spam detection in social bookmarking systems %U = http://doi.acm.org/10.1145/2024288.2024306

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.

@inproceedings{krause2008antisocial, author = {Krause, Beate and Schmitz, Christoph and Hotho, Andreas and Stumme, Gerd}, title = {The Anti-Social Tagger - Detecting Spam in Social Bookmarking Systems}, booktitle = {AIRWeb '08: Proceedings of the 4th International Workshop on Adversarial Information Retrieval on the Web}, publisher = {ACM}, address = {New York, NY, USA}, year = {2008}, pages = {61--68}, url = {http://airweb.cse.lehigh.edu/2008/submissions/krause_2008_anti_social_tagger.pdf}, doi = {10.1145/1451983.1451998}, isbn = {978-1-60558-159-0}, keywords = {2008, bookmarking, detection, itegpub, l3s, myown, seminar, spam, summer}, 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.} }

%0 = inproceedings %A = Krause, Beate and Schmitz, Christoph and Hotho, Andreas and Stumme, Gerd %B = AIRWeb '08: Proceedings of the 4th International Workshop on Adversarial Information Retrieval on the Web %C = New York, NY, USA %D = 2008 %I = ACM %T = The Anti-Social Tagger - Detecting Spam in Social Bookmarking Systems %U = http://airweb.cse.lehigh.edu/2008/submissions/krause_2008_anti_social_tagger.pdf

@inproceedings{FalBarSpi07, author = {Falkowski, Tanja and Barth, Anja and Spiliopoulou, Myra}, title = {DENGRAPH: A Density-based Community Detection Algorithm}, booktitle = {In Proc. of the 2007 IEEE / WIC / ACM International Conference on Web Intelligence,}, year = {2007}, pages = {112-115}, url = {http://wwwiti.cs.uni-magdeburg.de/~tfalkows/publ/2007/WI_FalBarSpi07.pdf}, keywords = {algorithm, based, clustering, community, density, detection} }

%0 = inproceedings %A = Falkowski, Tanja and Barth, Anja and Spiliopoulou, Myra %B = In Proc. of the 2007 IEEE / WIC / ACM International Conference on Web Intelligence, %D = 2007 %T = DENGRAPH: A Density-based Community Detection Algorithm %U = http://wwwiti.cs.uni-magdeburg.de/~tfalkows/publ/2007/WI_FalBarSpi07.pdf

As the number of resources on the web exceeds by far the number of
cuments one can track, it becomes increasingly difficult to remain
to date on ones own areas of interest. The problem becomes more
vere with the increasing fraction of multimedia data, from which
is difficult to extract some conceptual description of their
ntents.

ne way to overcome this problem are social bookmark tools, which
e rapidly emerging on the web. In such systems, users are setting
lightweight conceptual structures called folksonomies, and
ercome thus the knowledge acquisition bottleneck. As more and more
ople participate in the effort, the use of a common vocabulary
comes more and more stable. We present an approach for discovering
pic-specific trends within folksonomies. It is based on a
fferential adaptation of the PageRank algorithm to the triadic
pergraph structure of a folksonomy. The approach allows for any
nd of data, as it does not rely on the internal structure of the
cuments. In particular, this allows to consider different data
pes in the same analysis step. We run experiments on a large-scale
al-world snapshot of a social bookmarking system.

@inproceedings{hotho2006trend, author = {Hotho, Andreas and Jäschke, Robert and Schmitz, Christoph and Stumme, Gerd}, title = {Trend Detection in Folksonomies}, editor = {Avrithis, Yannis S. and Kompatsiaris, Yiannis and Staab, Steffen and O'Connor, Noel E.}, booktitle = {Proc. First International Conference on Semantics And Digital Media Technology (SAMT) }, series = {LNCS}, publisher = {Springer}, address = {Heidelberg}, year = {2006}, volume = {4306}, pages = {56-70}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2006/hotho2006trend.pdf}, isbn = {3-540-49335-2}, keywords = {2006, UniK, detection, folkrank, folksonomy, hotho, intranet, itegpub, jaeschke, l3s, myown, nepomuk, pagerank, schmitz, stumme, tagorapub, trend, triadic}, abstract = {As the number of resources on the web exceeds by far the number of
cuments one can track, it becomes increasingly difficult to remain
to date on ones own areas of interest. The problem becomes more
vere with the increasing fraction of multimedia data, from which
is difficult to extract some conceptual description of their
ntents.

ne way to overcome this problem are social bookmark tools, which
e rapidly emerging on the web. In such systems, users are setting
lightweight conceptual structures called folksonomies, and
ercome thus the knowledge acquisition bottleneck. As more and more
ople participate in the effort, the use of a common vocabulary
comes more and more stable. We present an approach for discovering
pic-specific trends within folksonomies. It is based on a
fferential adaptation of the PageRank algorithm to the triadic
pergraph structure of a folksonomy. The approach allows for any
nd of data, as it does not rely on the internal structure of the
cuments. In particular, this allows to consider different data
pes in the same analysis step. We run experiments on a large-scale
al-world snapshot of a social bookmarking system.} }

%0 = inproceedings %A = Hotho, Andreas and Jäschke, Robert and Schmitz, Christoph and Stumme, Gerd %B = Proc. First International Conference on Semantics And Digital Media Technology (SAMT) %C = Heidelberg %D = 2006 %I = Springer %T = Trend Detection in Folksonomies %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2006/hotho2006trend.pdf

Ein wichtiger Baustein des neu entdeckten World Wide Web - des "`Web 2.0"' - stellen
lksonomies dar. In diesen Systemen können Benutzer gemeinsam Ressourcen verwalten und
t Schlagwörtern versehen. Die dadurch entstehenden begrifflichen Strukturen stellen
n interessantes Forschungsfeld dar. Dieser Artikel untersucht Ansätze und Wege zur
tdeckung und Strukturierung von Nutzergruppen ("Communities") in Folksonomies.

@inproceedings{jaeschke2006wege, author = {Jäschke, Robert and Hotho, Andreas and Schmitz, Christoph and Stumme, Gerd}, title = {Wege zur Entdeckung von Communities in Folksonomies}, editor = {Braß, Stefan and Hinneburg, Alexander}, booktitle = {Proc. 18. Workshop Grundlagen von Datenbanken}, publisher = {Martin-Luther-Universität }, address = {Halle-Wittenberg}, year = {2006}, pages = {80-84}, url = {http://www.kde.cs.uni-kassel.de/stumme/papers/2006/jaeschke2006wege.pdf}, keywords = {2006, bibsonomy, communities, community, detection, itegpub, l3s, myown, nepomuk, tagging}, abstract = {Ein wichtiger Baustein des neu entdeckten World Wide Web -- des "`Web 2.0"' -- stellen
lksonomies dar. In diesen Systemen können Benutzer gemeinsam Ressourcen verwalten und
t Schlagwörtern versehen. Die dadurch entstehenden begrifflichen Strukturen stellen
n interessantes Forschungsfeld dar. Dieser Artikel untersucht Ansätze und Wege zur
tdeckung und Strukturierung von Nutzergruppen ("Communities") in Folksonomies.} }

%0 = inproceedings %A = Jäschke, Robert and Hotho, Andreas and Schmitz, Christoph and Stumme, Gerd %B = Proc. 18. Workshop Grundlagen von Datenbanken %C = Halle-Wittenberg %D = 2006 %I = Martin-Luther-Universität %T = Wege zur Entdeckung von Communities in Folksonomies %U = http://www.kde.cs.uni-kassel.de/stumme/papers/2006/jaeschke2006wege.pdf

@article{kumar99trawling, author = {Kumar, Ravi and Raghavan, Prabhakar and Rajagopalan, Sridhar and Tomkins, Andrew}, title = {Trawling the Web for emerging cyber-communities}, journal = {Computer Networks }, year = {1999}, volume = {31}, number = {11--16}, pages = {1481--1493}, url = {citeseer.ist.psu.edu/kumar99trawling.html}, keywords = {communities, community, detection, web} }

%0 = article %A = Kumar, Ravi and Raghavan, Prabhakar and Rajagopalan, Sridhar and Tomkins, Andrew %D = 1999 %T = Trawling the Web for emerging cyber-communities %U = citeseer.ist.psu.edu/kumar99trawling.html