Krause, B.; Schmitz, C.; Hotho, A. & Stumme, G.: The Anti-Social Tagger - Detecting Spam in Social Bookmarking Systems. AIRWeb '08: Proceedings of the 4th International Workshop on Adversarial Information Retrieval on the Web. New York, NY, USA: ACM, 2008, S. 61-68
[Volltext]
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, classification, folksonomy, spam, tagging, ol_web2.0, widely_related},
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.}
}
Bade, K. & Benz, D.: Evaluation Strategies for Learning Algorithms of Hierarchical Structures. Proceedings of the 32nd Annual Conference of the German Classification Society - Advances in Data Analysis, Data Handling and Business Intelligence (GfKl 2008). Berlin-Heidelberg: Springer, 2008Studies in Classification, Data Analysis, and Knowledge Organization
[Volltext]
Several learning tasks comprise hierarchies. Comparison with a "goldstandard" is often performed to evaluate the quality of a learned hierarchy. We assembled various similarity metrics that have been proposed in different disciplines and compared them in a unified interdisciplinary framework for hierarchical evaluation which is based on the distinction of three fundamental dimensions. Identifying deficiencies for measuring structural similarity, we suggest three new measures for this purpose, either extending existing ones or based on new ideas. Experiments with an artificial dataset were performed to compare the different measures. As shown by our results, the measures vary greatly in their properties.
@inproceedings{bade2008evaluation,
author = {Bade, Korinna and Benz, Dominik},
title = {Evaluation Strategies for Learning Algorithms of Hierarchical Structures},
booktitle = {Proceedings of the 32nd Annual Conference of the German Classification Society - Advances in Data Analysis, Data Handling and Business Intelligence (GfKl 2008)},
series = {Studies in Classification, Data Analysis, and Knowledge Organization},
publisher = {Springer},
address = {Berlin-Heidelberg},
year = {2008},
note = {in press},
url = {http://www.kde.cs.uni-kassel.de/pub/pdf/bade2008evaluation.pdf},
keywords = {2008, evaluation_strategies, hiearchies, itegpub, myown, ol_web2.0, widely_related},
abstract = {Several learning tasks comprise hierarchies. Comparison with a "goldstandard" is often performed to evaluate the quality of a learned hierarchy. We assembled various similarity metrics that have been proposed in different disciplines and compared them in a unified interdisciplinary framework for hierarchical evaluation which is based on the distinction of three fundamental dimensions. Identifying deficiencies for measuring structural similarity, we suggest three new measures for this purpose, either extending existing ones or based on new ideas. Experiments with an artificial dataset were performed to compare the different measures. As shown by our results, the measures vary greatly in their properties.}
}
Benz, D.; Grobelnik, M.; Hotho, A.; Jäschke, R.; Mladenic, D.; Servedio, V. D. P.; Sizov, S. & Szomszor, M.: Analyzing Tag Semantics Across Collaborative Tagging Systems. In: Alani, H.; Staab, S. & Stumme, G. (Hrsg.): Proceedings of the Dagstuhl Seminar on Social Web Communities. 2008
[Volltext]
The objective of our group was to exploit state-of-the-art Information Retrieval methods for finding associations and dependencies between tags, capturing and representing differences in tagging behavior and vocabulary of various folksonomies, with the overall aim to better understand the semantics of tags and the tagging process. Therefore we analyze the semantic content of tags in the Flickr and Delicious folksonomies. We find that: tag context similarity leads to meaningful results in Flickr, despite its narrow folksonomy character; the comparison of tags across Flickr and Delicious shows little semantic overlap, being tags in Flickr associated more to visual aspects rather than technological as it seems to be in Delicious; there are regions in the tag-tag space, provided with the cosine similarity metric, that are characterized by high density; the order of tags inside a post has a semantic relevance.
@inproceedings{benz2008analyzing,
author = {Benz, Dominik and Grobelnik, Marko and Hotho, Andreas and Jäschke, Robert and Mladenic, Dunja and Servedio, Vito D. P. and Sizov, Sergej and Szomszor, Martin},
title = {Analyzing Tag Semantics Across Collaborative Tagging Systems},
editor = {Alani, Harith and Staab, Steffen and Stumme, Gerd},
booktitle = {Proceedings of the Dagstuhl Seminar on Social Web Communities},
year = {2008},
number = {08391},
url = {http://www.kde.cs.uni-kassel.de/pub/pdf/benz2008analyzing.pdf},
keywords = {2008, dagstuhl, iin2009, itegpub, myown, tag_semantics, tagorapub, ol_web2.0, widely_related},
abstract = {The objective of our group was to exploit state-of-the-art Information Retrieval methods for finding associations and dependencies between tags, capturing and representing differences in tagging behavior and vocabulary of various folksonomies, with the overall aim to better understand the semantics of tags and the tagging process. Therefore we analyze the semantic content of tags in the Flickr and Delicious folksonomies. We find that: tag context similarity leads to meaningful results in Flickr, despite its narrow folksonomy character; the comparison of tags across Flickr and Delicious shows little semantic overlap, being tags in Flickr associated more to visual aspects rather than technological as it seems to be in Delicious; there are regions in the tag-tag space, provided with the cosine similarity metric, that are characterized by high density; the order of tags inside a post has a semantic relevance.}
}