A Framework for Intelligent Notification Management in Multitasking Domains

In this work, we focus on one class of interruption, notifications in the desktop, and present one solution to managing such notifications--- intelligently timing their delivery. Our solution is based on a deep theoretical understanding of how humans process information and what moments during a user's task execution exhibit lower mental workload. We leverage breakpoints, transitions between units of action as potential moments for presenting notifications, as we empirically show these moments to have lower mental workload. Through a series of empirical studies, we demonstrate how presenting interruptions at breakpoints lowers interruption costs and how the cost varies based on the granularity of the breakpoint, how these breakpoints can be detected using known task structures and how breakpoints can be detected without any knowledge of the underlying task. We develop O ASIS, a computational framework that can detect and differentiate three levels of breakpoints with reasonable accuracy without requiring any complex machinery. OASIS is the first system of its kind that can detect breakpoints and schedule notifications. We evaluate how O ASIS picks breakpoints for novel users and novel tasks, and how scheduling notifications at breakpoints reduces interruption costs. This work provides the first empirical evidence that intelligent notification management benefits the end user and contributes new lessons for designing effective notification management systems.

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Computer Science

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2015

Author dc:creator

• Iqbal, Shamsi T.

Contributors dc:contributor

• Bailey, Brian P.

• Computer Science

Language dc:language

eng

Identifier

(MiAaPQ)AAI3337802

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/81830