Saman Kamran

Introduction Computing semantic relatedness and defining ontologies to describe particular domain knowledge is one of the most critical and costly steps for developing the semantic web. In recent years, much research attention has been given to semantic techniques of Information Retrieval (IR) methods, whose results are highly dependent on the quality of the resources that are used by them for knowledge extraction. One of the ... Copyright is held by the author/owner(s). CSCW 2011, March 19–23, 2011, Hangzhou, China. ACM 978-1-4503-0556-3/11/03.

ABSTRACT Taggers in social tagging systems have the main role in giving identities to the objects. Tagged objects also represent perception of their taggers about them and can define identities of their taggers in return. Consequently, identities that are assigned to the objects and taggers have effect on the quality of their categorization and communities formation around them. Tags in social semantic tagging systems have formal definitions because they are mapped to the concepts that are defined in ontologies. Semantic tags are not only able to improve quality of tag assignments by solving some common tags ambiguity problems related to classic folksonomy systems (i.e., in particular polysemy and synonymy), but also to provide some meta data on top of the social relations based on contribution of taggers around semantic tags. Those meta data may be exploited to form dynamic communities which addresses the problems of lack of commonly agreed and evolving meaning of tags in social semantic tagging systems. This paper proposes an approach to form dynamic communities of related taggers around the tagged objects. Because our perceptions in each specific area of knowledge is evolving over time, the goal of our approach is also to evolve the represented knowledge in semantic tagging systems dynamically according to the latest perception of the related users.