Supporting Semantic Annotation in Collaborative Workspaces with Knowledge based on Linked Open Data

The management of shared resources on the Web has become one of the most pervasive activities in everyday life, but the heterogeneity of tools and resource types (documents, emails, Web sites, etc.) usually causes users to be lost and to spend a lot of time in organizing resources and tasks. Structured semantic annotation can provide a smart support to collaborative resource organization, but, as demonstrated by our user studies, users have often to deal with ambiguous or unknown expressions, suggested by the system or by other users. As a consequence, it is important to provide them with an "explanation" of unclear annotations, which can be based on formally encoded domain knowledge, retrieved from the LOD Cloud. We chose commonsense geospatial knowledge to implement a proof-of-concept prototype providing such “explanations”. After a brief presentation of the background, represented by the SemT++ project, we describe the approach and present a user evaluation of it.