Semantic Enrichment of Folksonomy Tagspaces

The usability and the strong social dimension of the Web2.0 applications has encouraged users to create, annotate and share their content thus leading to a rich and content-intensive Web. Despite that, the Web2.0 content lacks the explicit semantics that would allow it to be used in large-scale intelligent applications. At the same time the advances in Semantic Web technologies imply a promising potential for intelligent applications capable to integrate distributed content and knowledge from various heterogeneous resources. We present FLOR a tool that performs semantic enrichment of folksonomy tagspaces by exploiting online ontologies, thesauri and other knowledge sources. 1 Background and Research Problem The large-scale content annotation and metadata generation has been realised as Web2.0 applications have become very popular. Despite that, Web2.0 lacks the explicit semantics that would allow the content to be used in large-scale intelligent applications. At the same time the advances in Semantic Web technologies imply a promising potential for intelligent applications capable to integrate distributed content and knowledge from various heterogeneous resources. There is significant discussion that the combination of Semantic Web and Web2.0 will lead to an interoperable, intelligent Web ([4, 8, 10]). The goal of this work is to identify methods for the automatic semantic enrichment of Web2.0 generated content with a focus on folksonomies. Folksonomies are Web2.0 systems whose basic elements are users, resources and tags. A resource is a content object depending on the folksonomy (a photo in Flickr, a bookmark in Del.icio.us, a video in YouTube and so on). A tag can be any sequence of characters a user can attach to a resource. However the semantics of tags, and as a result the semantics of the resources, are not known and are not explicitly stated. This often hampers the resource retrieval within the individual system as well as the integration of resources in cross platform applications. The goal of this work is to identify the meaning of the tags attached to a resource, to obtain the formal semantics that correspond to these tags 1 http://www.Flickr.com 2 http://del.icio.us 3 http://www.youtube.com and to attach the formal semantics to the resource, automatically creating in that way a semantic layer on top of folksonomy tagspaces. The realisation of the above raises the following research questions. – How can folksonomies’ tagspaces be semantically enriched automatically? This research question can be further analysed into the following questions. How to discover automatically the meaning of tags based on their context? How can the Semantic Web be exploited for the semantic enrichment of the tags and what other resources are required in case the Semantic Web falls short of that task? – How can the enriched tagspaces be evaluated in terms of content retrieval against the non enriched tagspaces? What performance measures should be established to measure content retrieval in folksonomies before and after the semantic enrichment? In the following we describe the existing research on folksonomies and present our work.