Toward Social Role-Based Interruptibility Management

Pervasive and ubiquitous computing facilitates immediate access to information in the sense of always-on. Information, such as news, messages, or reminders, can significantly enhance our daily routines but are rendered useless disturbing when not being aligned with intrinsic interruptibility preferences. Attention management systems use machine learning identify short-term opportune moments, so that delivery leads fewer interruptions. Humans’ preferences—established for across social roles life domains—would complement attention interruption approaches. In this article, we present comprehensive results toward role-based management. Our approach combines on-device sensing theories from science form a personalized two-stage classification model. Finally, discuss challenges current future AI-driven concerning privacy, ethical issues, directions.