Hyperincident connected components of tagging networks Export

@inproceedings{citeulike:5031993, abstract = {Data created by social bookmarking systems can be described as 3-partite 3-uniform hypergraphs connecting documents, users, and tags (tagging networks), such that the toolbox of complex network analysis can be applied to examine their properties. One of the most basic tools, the analysis of connected components, however cannot be applied meaningfully: Tagging networks tend to be almost entirely connected. We therefore propose a generalization of connected components, m -hyperincident connected components. We show that decomposing tagging networks into 2-hyperincident connected components yields a characteristic component distribution with a salient giant component that can be found across various datasets. This pattern changes if the underlying formation process changes, for example, if the hypergraph is constructed from search logs, or if the tagging data is contaminated by spam: It turns out that the second- to 129th largest components of the spam-labeled Bibsonomy dataset are inhabited exclusively by spam users. Based on these findings, we propose and unsupervised method for spam detection.}, address = {New York, NY, USA}, author = {Neubauer, Nicolas and Obermayer, Klaus}, booktitle = {HT '09: Proceedings of the 20th ACM conference on Hypertext and hypermedia}, citeulike-article-id = {5031993}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1557914.1557954}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1557914.1557954}, doi = {10.1145/1557914.1557954}, isbn = {978-1-60558-486-7}, keywords = {best-paper, ht09, network-analysis, spam, tagging}, location = {Torino, Italy}, pages = {229--238}, posted-at = {2009-07-01 12:40:36}, priority = {0}, publisher = {ACM}, title = {Hyperincident connected components of tagging networks}, url = {http://dx.doi.org/10.1145/1557914.1557954}, year = {2009} }

TY - CONF ID - citeulike:5031993 L3 - citeulike-article-id:5031993 N2 - Data created by social bookmarking systems can be described as 3-partite 3-uniform hypergraphs connecting documents, users, and tags (tagging networks), such that the toolbox of complex network analysis can be applied to examine their properties. One of the most basic tools, the analysis of connected components, however cannot be applied meaningfully: Tagging networks tend to be almost entirely connected. We therefore propose a generalization of connected components, m -hyperincident connected components. We show that decomposing tagging networks into 2-hyperincident connected components yields a characteristic component distribution with a salient giant component that can be found across various datasets. This pattern changes if the underlying formation process changes, for example, if the hypergraph is constructed from search logs, or if the tagging data is contaminated by spam: It turns out that the second- to 129th largest components of the spam-labeled Bibsonomy dataset are inhabited exclusively by spam users. Based on these findings, we propose and unsupervised method for spam detection. CY - Torino, Italy SN - 978-1-60558-486-7 AD - New York, NY, USA EP - 238 TI - Hyperincident connected components of tagging networks PB - ACM T2 - HT '09: Proceedings of the 20th ACM conference on Hypertext and hypermedia SP - 229 KW - best-paper KW - ht09 KW - network-analysis KW - spam KW - tagging AU - Neubauer, Nicolas AU - Obermayer, Klaus PY - 2009/// UR - http://dx.doi.org/10.1145/1557914.1557954 ER -