|Title||Co-Clustering Tags and Social Data Sources|
|Publication Type||Conference Paper|
|Year of Publication||2008|
|Authors||Giannakidou, Eirini, Vassiliki A. Koutsonikola, Athena Vakali, and Yiannis Kompatsiaris|
Under social tagging systems, a typical Web 2.0 application,users label digital data sources by using freely chosentextual descriptions (tags). Poor retrieval in the aforementionedsystems remains a major problem mostly due toquestionable tag validity and tag ambiguity. Earlier clusteringtechniques have shown limited improvements, since theywere based mostly on tag co-occurrences. In this paper,a co-clustering approach is employed, that exploits jointgroups of related tags and social data sources, in whichboth social and semantic aspects of tags are consideredsimultaneously. Experimental results demonstrate the effi-ciency and the beneficial outcome of the proposed approachin correlating relevant tags and resources.
Co-Clustering Tags and Social Data Sources