A method, system, and tools for intelligent interruption management

Interrupting users engaged in tasks typically has negative effects on their task completion time, error rate, and affective state. Empirical research has shown that these negative effects can be mitigated by deferring interruptions until more opportune moments in a user's task sequence. However, existing systems that reason about when to interrupt do not have access to task models that would allow for such finer-grained temporal reasoning. We outline our method of finding opportune moments that links a physiological measure of workload with task modeling techniques and theories of attention. We describe the design and implementation of our interruption management system, showing how it can be used to specify and monitor practical, representative user tasks. We discuss our ongoing empirical work in this area, and how the use of our framework may enable attention aware systems to consider a user's position in a task when reasoning about when to interrupt.