Predicting human interruptibility with sensors

Abstract

A person seeking another person's attention is normally able to quickly assess how interruptible the other person currently is. Such assessments allow behavior that we consider natural, socially appropriate, or simply polite. This is in sharp contrast to current computer and communication systems, which are largely unaware of the social situations surrounding their usage and the impact that their actions have on these situations. If systems could model human interruptibility, they could use this information to negotiate interruptions at appropriate times, thus improving human computer interaction.This article presents a series of studies that quantitatively demonstrate that simple sensors can support the construction of models that estimate human interruptibility as well as people do. These models can be constructed without using complex sensors, such as vision-based techniques, and therefore their use in everyday office environments is both practical and affordable. Although currently based on a demographically limited sample, our results indicate a substantial opportunity for future research to validate these results over larger groups of office workers. Our results also motivate the development of systems that use these models to negotiate interruptions at socially appropriate times.

Using Decision-Theoretic Experience Sampling to Build Personalized Mobile Phone Interruption Models

“…Studies have shown that human interruption in offices can be captured accurately by simple sensors such as these [6,9], and other studies have found that users decide whether to answer their phones based on their activity, location, and who is callingall of which are becoming more observable using current phone sensors [7,15,16]. With new applications to classify interruption preferences and react based on these predictions, it is not clear what accuracy level is acceptable for users.…”

Mixed-Initiative Context Filtering and Group Selection for Improving Ubiquitous Help Systems

“…Such understanding about others allows behavior that is considered natural, socially appropriate, or simply polite. As Fogarty et al [5] have identified the fact half a decade ago, current computer and communication systems are still largely unaware of the social situations surrounding their usage and the impact that their actions have on these situations. There have been several research attempts, but there is not much development in this regards.…”

Awareness Solutions for Informal Communication Negotiation Support at Work

“…Informal communication between coworkers is considered as an optimal way to exchange rapid feedback, share local context and reference common depictions [2]. But it comes at a cost: interruptions.…”

“…However, once initiated at right times they serve as natural breaks and provide content for expressive interaction between colleagues. Current solutions supporting handling interruptions assume the interruptee's availability to be the best predictor of an appropriate interruption moment [2]. Yet, interruptors seem not to fully adhere to those availability indications as the proposed systems fail to help them convey their communicative needs.…”