How Busy Are You?

Abstract

Smartphones frequently notify users about newly available messages or other notifications. It can be very disruptive when these notifications interrupt users while they are busy. Our work here is based on the observation that people usually exhibit different levels of busyness at different contexts. This means that classifying users' interruptibility as a binary status, interruptible or not interruptible, is not sufficient to accurately measure their availability towards smartphone interruptions. In this paper, we propose, implement and evaluate a two-stage hierarchical model to predict people's interruptibility intensity. Our work is the first to introduce personality traits into interruptibility prediction model, and we found that personality data improves the prediction significantly. Our model bootstraps the prediction with similar people's data, and provides a good initial prediction for users whose individual models have not been trained on their own data yet. Overall prediction accuracy of our model can reach 66.1%.We present the following four major contributions: 1) We propose a two-stage hierarchical interruptibility prediction model. In the first stage, our model predicts (with 75% accuracy) whether a user will react to an interruption

The effects of fragmented and sticky smartphone use on distraction and task delay

“…Conversely, sticky smartphone use may be perceived as less distractive than fragmented use as it is more contiguous, thereby causing fewer interruptions in adolescents' attention. Existing research has indeed shown that people felt less distracted when smartphone interruptions lasted longer (Yuan et al, 2017). Thus, we hypothesize: H1c: The association between fragmented smartphone use and distraction is stronger than the association between sticky smartphone use and distraction.…”

“…Studies have shown that sticky media are entertaining (Brinberg et al, 2023), interactive (Furner et al, 2014; Nandi et al, 2021), and engaging (Zhang et al, 2017), and may elicit a state of flow in their users (Hoffman & Novak, 1996; Montag et al, 2019). This state of flow is characterized by absolute concentration and full absorption in the medium and causes a distorted perception of time (Hoffman & Novak, 1996; Roberts & David, 2023).…”

A Survey of Attention Management Systems in Ubiquitous Computing Environments

“…5 . It is worth to note that not only physical activities [46,77,99] or interactions [35,91], but also more expressive concepts such as complex activities [54], engagement levels [84], even personal traits [64,119] are frequently used in attention management systems. To infer such contextual information, various machine learning algorithms e.g., J48 [77,99], K-Means [54], or Support Vector Machines [99] are typically trained and…”

“…For example, explicit measures include experience sampling methods/ecological momentary assessments (ESM/EMA) where individuals are asked to rate their current experience in-situ. In this regard, the NASA-TLX is frequently used, in particular, to assess models that are based on cognitive theories and frameworks such as mental workload [122], level of task engagement [84], or level of interruptibility [119]. NASA-TLX is a multi-dimensional rating tool which compromises six weighted scales including mental, physical, and temporal demand, as well as performance, effort, and frustration [45].…”