| Summary: | The Semantic Web Community has invested significant research efforts in developing systems for Semantic Web search and exploration. But while it has been easy to assess the systems' computational efficiency, it has been much harder to assess how well different semantic systems' user interfaces help their users. In this article, we propose and demonstrate the use of a benchmark for evaluating such user interfaces, similar to the TREC benchmark for evaluating traditional search engines. Our benchmark includes a set of typical user tasks and a well-defined procedure for assigning a measure of performance on those tasks to a semantic system. We demonstrate its application to two such system, Virtuoso and Rhizomer. We intend for this work to initiate a community conversation that will lead to a generally accepted framework for comparing systems and for measuring, and thus encouraging, progress towards better semantic search and exploration tools.
|
|---|
