A Survey of Attention Management Systems in Ubiquitous Computing Environments

Abstract

Today's information and communication devices provide always-on connectivity, instant access to an endless repository of information, and represent the most direct point of contact to almost any person in the world. Despite these advantages, devices such as smartphones or personal computers lead to the phenomenon of attention fragmentation, continuously interrupting individuals' activities and tasks with notifications. Attention management systems aim to provide active support in such scenarios, managing interruptions, for example, by postponing notifications to opportune moments for information delivery. In this article, we review attention management system research with a particular focus on ubiquitous computing environments. We first examine cognitive theories of attention and extract guidelines for practical attention management systems. Mathematical models of human attention are at the core of these systems, and in this article, we review sensing and machine learning techniques that make such models possible. We then discuss design challenges towards the implementation of such systems, and finally, we investigate future directions in this area, paving the way for new approaches and systems supporting users in their attention management.:2 • C. Anderson et al. Key takeaway points⋆ Attention is captured and steered by external and internal stimuli, while stimulus properties, such as its duration, location, intensity, etc., impact the user's reaction to the stimulus. Multimodal alert types, e.g., sound, light, vibration, and multiple device environments call for a coordinated judicious use of alerting in ubiquitous computing. ⋆ Limited cognitive capacities and threaded task processing imply that, in order to minimize disruptions, interruptions need to arrive at task boundaries or during routine tasks, should allow for task state rehearsal, and support context retrieval through hints presented to the user after an interruption. ⋆ Sensor data from ubiquitous computing devices reveals a user's location, physical activity, collocation with other people, and other information of a user's context that can be related to interruptibility. Next generation wearable devices and personalized machine learning models promise to bring us closer to direct inference of a user's cognitive processes. ATTENTION AND INTERRUPTION: DEFINITIONS AND STRATEGIESIn this section, we review definitions of the terms attention and interruption. We examine the connection between attention shifting and interruptions and discuss how interruptions can be handled through attention management systems in ubiquitous environments. What is Attention?There is no common understanding of attention in the literature. Attention is often considered as selective processing of incoming sensory information [33], with limited capacity [23] and reactive and deliberate processes [92]. Attention is also referred to as the ability to ignore irrelevant information [24]. The process of selecting stimuli can be voluntary or be steered by external events. The former ty...

Wireless Ranging for Contactless Cognitive Load Inference in Ubiquitous Computing

“…The underlying causes for such disruptive effects stem from the limitations of human cognitive processing capacities, in particular, procedural memory resources. Interaction initiated by a computing device at moments when a user is engaged in another (primary) task requires, in the best case, the conclusion of the primary task, while in the worst case it requires that the primary task's problem state is stored in the declarative memory, before the new interaction is handled (Anderson et al, 2018;Borst et al, 2010). The latter case is especially evident when the primary task is complex.…”

Intelligent Task Recognition: Towards Enabling Productivity Assistance in Daily Life

“…Others focused on mining behavioral rules from smartphones in order to manage incoming calls [25]. Sensor data and machine learning have been exploited to construct attention management systems [2] so as to predict when a notification should be sent and to which device [17] in order to improve the user experience. Recently, Ren et al investigated how to predict users' demographics by considering their CPS behaviors [23].…”

Moment-to-Moment Continuous Attention Fluctuation Monitoring through Consumer-Grade EEG Device

“…Maintaining one’s attention for a period of time, and selectively concentrating on a stimulus or task while ignoring others require effort, and vary based on the individual’s ability to withstand cognitive load [ 2 ]. With the rising scale of distractions presented as part of modern living, several research works dived into building interfaces or systems to facilitate attention processes, e.g., attentional user interface [ 3 ], attention-aware systems [ 4 ] and attention management systems [ 5 ]. The fundamental step in building these systems is measuring users’ attention states.…”