Topical tags vs non-topical tags

摘要: In this paper we investigate whether it is possible to create a computational approach that allows us distinguish topical tags i.e. talking about the topic of resource and non-topical describing aspects are not related its in folksonomies, way correlates with humans. Towards goal, collected 21 million 1.2 unique terms from Delicious developed an unsupervised statistical algorithm classifies such by applying word space model adapted folksonomy space. Our analyses co-occurrence network target tag exploits graph-based metrics for their classification. We validated outcomes against reference classification made humans on limited number three separate tests. The analysis our shows, some cases, consistent disagreement among between what constitutes tag, suggests rise new category overly generic umbrella tags.