BusyBody: creating and fielding personalized models of the cost of interruption

Interest has been growing in opportunities to build and deploy statistical models that can infer a computer user’s current interruptability from computer activity and relevant contextual information. We describe a system that intermittently asks users to assess their perceived interruptability during a training phase and that builds decision-theoretic models with the ability to predict the cost of interrupting the user. The models are used at run-time to compute the expected cost of interruptions, providing a mediator for incoming notifications, based on a consideration of a user’s current and recent history of computer activity, meeting status, location, time of day, and whether a conversation is detected. Categories and Subject Descriptors

• Type: Conference
• Year: 2004
• Where: CSCW
• Authors: Eric Horvitz, Paul Koch, Johnson Apacible
• Keywords: Builds Decision-theoretic Models, CSCW 2004, Relevant Contextual Information, Social Sciences, Statistical Models