earticle

영어

With the Semantic Web people participate more actively in the building of information and take on an active role in enriching collaborative knowledge bases with user-generated contents. Moreover, new online resources have quickly gained impact on information management, such as the social bookmarking systems, which enable users to store, manage and share tagged Web content through folksonomies. These social tools allow users to associate free chosen keywords (tags) with Web content with the aim of providing an efficient navigation system through the heterogeneous amount of information available on the Web. However, the association of tags is totally arbitrary so that the use of synonyms, homonyms and new slang terms often hampers the Web information retrieval. Our project proposes the development of an innovative social bookmarking system based on a priori classification with semantic tags and structured categories extracted from online linguistic resources, which aims at disambiguating Web Content. According to this approach, each content will be described through two axes: a vertical one, concerning a hierarchical taxonomic classification and a horizontal one, dealing with a folksonomic classification. The final aim is to create a collaborative knowledge base of semantically disambiguated contents and to achieve more precise results in Web retrieval.