In this paper, we give an overview of a system (CAIMAN) that can facilitate the exchange of relevant documents between geographically dispersed people in Communities of Interest. The nature of Communities of Interest prevents the creation and enforcement of a common organizational scheme for documents, to which all community members adhere. Each community member organizes her documents according to her own categorization scheme (ontology). CAIMAN exploits this personal ontology, which is essentially the perspective of a user on a domain, for information retrieval. Related documents are retrieved on a concept granularity level from a central community document repository. To find the related concepts in the queried ontology, CAIMAN performs an ontology mapping. The ontology mapping in CAIMAN is based on a novel approach, which considers the concepts in an ontology implicitly represented by the documents assigned to each concept. Using machine learning techniques for text classification...
Martin S. Lacher, Georg Groh