A context-aware cost of interruption model for mobile devices

Abstract

Unwanted and untimely interruptions have been a major cause in the loss of productivity in recent years as they are mostly detrimental to the immediate task at hand. Multiple approaches have been proposed to address the problem of interruption by calculating cost of interruption. The cost of interruption (COI) gives as a measure the probabilistic value of harmfulness of an inopportune interruption. Bayesian Inference stands atop among the models that have been applied to calculate this COI. However Bayesian inference based models suffer from not being able to model context accurately in situations where priori, conditional probabilities and uncertainties exist while utilizing context information. Hence, this paper introduces Dempster-Shafer Theory of Evidence to model COI. Along the way, we also identify different contexts necessary for interruption management applications. We also show an illustrative example of a mobile interruption management application where the Dempster-Shafer theory is used to get a better measurement of whether to interrupt or not.