Interruptibility Estimation Based on Head Motion and PC Operation

Smartphone notifications frequently interrupt our daily lives, often at inopportune moments. We propose the decision-on-information-gain model, which extends the existing data collection convention to capture a range of interruptibility behaviour implicitly. Through a six-month in-the-wild study of 11,346 notifications, we find that this approach captures up to 125% more interruptibility cases. Secondly, we find different correlating contextual features for different behaviour using the approach and find that predictive models can be built with >80% precision for most users. However we note discrepancies in performance across labelling, training, and evaluation methods, creating design considerations for future systems.

show abstract

“…interruption habits) this is not unexpected. The performance is also similar to other recent studies (e.g., [7,16,40]),…”

Section: Results: How Well Can Response Behaviour Be Predicted?supporting

confidence: 91%

Reachable but not receptive: Enhancing smartphone interruptibility prediction by modelling the extent of user engagement with notifications

Turner

Allen

Whitaker

2017

Pervasive and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…Hudson et al focused on the situation of the worker and proposed a method using the seating position, voice, and PC operation [22]. Tanaka et al used head motion as an indication reflecting the worker's degree of engagement in a task [23]. Tani and Yamada demonstrated the effectiveness of using tabletop pressure [24].…”

Section: Methods For Estimating Interruptibilitymentioning

confidence: 99%

Predicting Uninterruptible Durations of Office Workers by Using Probabilistic Work Continuance Model

Shiratori

Fujimoto

Fujita

2020

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

In order not to disrupt a team member concentrating on his/her own task, the interrupter needs to wait for a proper time. In this research, we examined the feasibility of predicting prospective interruptible times of office workers who use PCs. An analysis of actual working data collected from 13 participants revealed the relationship between uninterruptible durations and four features, i.e. type of application software, rate of PC operation activity, activity ratio between keystrokes and mouse clicks, and switching frequency of application software. On the basis of these results, we developed a probabilistic work continuance model whose probability changes according to the four features. The leave-oneout cross-validation indicated positive correlations between the actual and the predicted durations. The medians of the actual and the predicted durations were 539 s and 519 s. The main contribution of this study is the demonstration of the feasibility to predict uninterruptible durations in an actual working scenario.

show abstract

“…The interruptibility estimation should also be more accurate. Use of more behavioral features such as user head motion, which roughly reflects changes in the worker's gaze target [45], appears promising. Use of physiological signals reflecting mental workload, such as pupil dilation [46], electrocardiogram (ECG), or electroencephalogram (EEG) [47], would also provide better estimates.…”

Section: Feasibility Of Improvements To Edmsmentioning

confidence: 99%

Development of E-mail Delivery Mediation System Based on Interruptibility and Its Evaluation in Daily Office Work Scenario

2019

Self Cite

View full text Add to dashboard Cite

Notifications of e-mail arrivals at inappropriate times disrupt workers engaged in intellectual activities and reduce their productivity. We propose an e-mail delivery mediation system to deal with this issue. The system suspends e-mail delivery and estimates users' interruptibility from their PC operation activities. Then, it delivers e-mail only when the estimated interruptibility matches certain delivery criteria, especially when a user switches applications. A long-term evaluation in a real office revealed that e-mail mediation based on the system's estimates of user interruptibility can shift a certain percentage of the notifications to task or subtask breakpoints or to times at which the user is less engaged in a task.

show abstract

Interruptibility Estimation Based on Head Motion and PC Operation

Cited by 17 publications

References 19 publications

Reachable but not receptive: Enhancing smartphone interruptibility prediction by modelling the extent of user engagement with notifications

Reachable but not receptive: Enhancing smartphone interruptibility prediction by modelling the extent of user engagement with notifications

Predicting Uninterruptible Durations of Office Workers by Using Probabilistic Work Continuance Model

Development of E-mail Delivery Mediation System Based on Interruptibility and Its Evaluation in Daily Office Work Scenario

Contact Info

Product

Resources

About