http://www.bibsonomy.org/rss/group/iteg/myownBibSonomy RSS Feed for /group/iteg/myownhttp://www.kde.cs.uni-kassel.de/ws/muse2011/hotho2011-05-24T09:47:28+02:002011 ecml mining myown pkdd social ubiquitous workshop http://www.dcs.warwick.ac.uk/~ssanand/RSWeb11/index.htmhotho2011-05-24T09:46:58+02:002011 myown recommender social systems web workshop HT2011 is the 22nd ACM conference on hyptertext and hypermedia. Eindhoven, The Netherlands, June 6-9, 2011http://www.ht2011.org/hotho2011-01-21T11:36:09+01:00acm conference ht2011 hypertext myown session track HT2011 is the 22nd ACM conference on hyptertext and hypermedia. Eindhoven, The Netherlands, June 6-9, 2011journals/ki/XX05d, Subgroup Discovery., 52-53, 2005, KI, 19, 4, http://dblp.uni-trier.de/db/journals/ki/ki19.html#XX05d, http://www.kuenstliche-intelligenz.de/index.php?id=no-6408&amp;tx_ki_pi1[showUid]=1123&amp;cHash=0a2459118chttp://dblp.uni-trier.de/db/journals/ki/ki19.html#XX05datzmueller2011-01-15T23:50:51+01:002005 discovery myown subgroup journals/ki/XX05d, Subgroup Discovery., 52-53, 2005, KI, 19, 4, http://dblp.uni-trier.de/db/journals/ki/ki19.html#XX05d, http://www.kuenstliche-intelligen<span class="info">...<div>journals/ki/XX05d, Subgroup Discovery., 52-53, 2005, KI, 19, 4, http://dblp.uni-trier.de/db/journals/ki/ki19.html#XX05d, http://www.kuenstliche-intelligenz.de/index.php?id=no-6408&amp;tx_ki_pi1[showUid]=1123&amp;cHash=0a2459118c</div></span>http://www.vikamine.orgatzmueller2010-12-06T23:23:03+01:00datamining myown vikamine View Andreas Hotho&#039;s professional profile. http://academic.research.microsoft.com/Author/1348132.aspxhotho2010-10-04T10:41:13+02:00academic microsoft myown researcher search View Andreas Hotho&#039;s professional profile.http://www.slideshare.net/dbenz/stop-thinking-start-tagging-tag-semantics-emerge-from-collaborative-verbositydbenz2010-05-04T16:32:42+02:002010 myown slides slideshare www2010 http://www.kde.cs.uni-kassel.de/ws/muse2010hotho2010-05-03T11:18:00+02:002010 data mining myown social web workshop Wenn sich die Tags im Web zu einem Begriffsnetz verknüpfen lassen, wird die Suche optimiert. Österreichische Forscher arbeiten daran.http://www.computerwoche.de/netzwerke/web/1934448/dbenz2010-05-02T17:16:35+02:00myown review www2010 Wenn sich die Tags im Web zu einem Begriffsnetz verknüpfen lassen, wird die Suche optimiert. Österreichische Forscher arbeiten daran.http://futurezone.orf.at/stories/1645573/dbenz2010-04-27T15:07:41+02:00interview markus_strohmaier myown orf orf.at strohmaier www2010 http://kmi.tugraz.at/workshop/MSM10/hotho2010-03-07T16:45:43+01:002010 canada hypertext media modeling myown social workshop tripartite http://videolectures.net/ecmlpkdd09_benz_csrsqt/dbenz2010-01-05T22:46:37+01:00ecmlpkdd itegpub myown talk tripartitehttp://www.ismll.uni-hildesheim.de/software/caribo/index_en.htmldbenz2009-07-30T13:43:56+02:00bookmark_classification caribo itegpub myown sitebar studienarbeit Social bookmarking systems and their emergent information structures, known as folksonomies, are increasingly important data sources for Semantic Web applications. A key question for harvesting semantics from these systems is how to extend and adapt traditional notions of similarity to folksonomies, and which measures are best suited for applications such as navigation support, semantic search, and ontology learning. Here we build an evaluation framework to compare various general folksonomy-based similarity measures derived from established information-theoretic, statistical, and practical measures. Our framework deals generally and symmetrically with users, tags, and resources. For evaluation purposes we focus on similarity among tags and resources, considering different ways to aggregate annotations across users. After comparing how tag similarity measures predict user-created tag relations, we provide an external grounding by user-validated semantic proxies based on WordNet and the Open Directory. We also investigate the issue of scalability. We find that mutual information with distributional micro-aggregation across users yields the highest accuracy, but is not scalable; per-user projection with collaborative aggregation provides the best scalable approach via incremental computations. The results are consistent across resource and tag similarity.http://www2009.eprints.org/65/dbenz2009-04-24T12:58:50+02:00attended itegpub myown www2009 Social bookmarking systems and their emergent information structures, known as folksonomies, are increasingly important data sources for Semantic Web appli<span class="info">...<div>Social bookmarking systems and their emergent information structures, known as folksonomies, are increasingly important data sources for Semantic Web applications. A key question for harvesting semantics from these systems is how to extend and adapt traditional notions of similarity to folksonomies, and which measures are best suited for applications such as navigation support, semantic search, and ontology learning. Here we build an evaluation framework to compare various general folksonomy-based similarity measures derived from established information-theoretic, statistical, and practical measures. Our framework deals generally and symmetrically with users, tags, and resources. For evaluation purposes we focus on similarity among tags and resources, considering different ways to aggregate annotations across users. After comparing how tag similarity measures predict user-created tag relations, we provide an external grounding by user-validated semantic proxies based on WordNet and the Open Directory. We also investigate the issue of scalability. We find that mutual information with distributional micro-aggregation across users yields the highest accuracy, but is not scalable; per-user projection with collaborative aggregation provides the best scalable approach via incremental computations. The results are consistent across resource and tag similarity.</div></span>mendation service which can be called via HTTP by BibSonomy&#039;s recommender when a user posts a bookmark or publication. All participating recommenders are called on each posting process, one of them is choosen to actually deliver the results to the user. We can then measure http://www.kde.cs.uni-kassel.de/ws/dc09/hotho2009-03-30T16:12:25+02:002009 challenge discovery ecml myown pkdd workshop mendation service which can be called via HTTP by BibSonomy&#039;s recommender when a user posts a bookmark or publication. All participating recommenders are c<span class="info">...<div>mendation service which can be called via HTTP by BibSonomy&#039;s recommender when a user posts a bookmark or publication. All participating recommenders are called on each posting process, one of them is choosen to actually deliver the results to the user. We can then measure </div></span>http://iasc2.diee.unica.it/iia2008/index.php/invited-speakers/hotho2008-11-25T16:40:05+01:002.0 2008 invited myown speaker web http://kcap09.stanford.edu/hotho2008-11-14T15:45:24+01:002009 conference kcap knowledge myown workshop http://www.ht2009.org/hotho2008-10-31T11:44:39+01:002009 chair conference ht09 hypertext link myown session track http://kmi.tugraz.at/workshop/KASW08/hotho2008-06-16T10:49:43+02:002008 mining myown social sw workshop SPECIAL SESSION ON MINING OF SOCIAL MEDIA; Paper Submission: June 13http://samt2008.uni-koblenz.de/hotho2008-06-06T17:39:49+02:002008 conference myown session SPECIAL SESSION ON MINING OF SOCIAL MEDIA; Paper Submission: June 13