Information access in context

Our central claim is that user interactions with productivity applications (e.g, word processors, Web browsers, etc.) provide rich contextual informat ion that can be leveraged to support just-in-time access to task-relevant i nformation. As evidence for our claim, we present Watson, a system which ga thers contextual information in the form of the text of the document the us er is manipulating, in order to proactively retrieve documents from distrib uted information repositories related to task at hand, as well as process e xplicit requests in the context of this task. We close by describing the re sults of several experiments with Watson, which show it consistently provid es useful information to its users. The experiments also suggest that, cont rary to the assumptions of many system designers, similar documents are not necessarily useful documents in the context of a particular task. (C) 2001 Elsevier Science B.V. All rights reserved.