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

Turner, Liam D. ORCID: https://orcid.org/0000-0003-4877-5289, Allen, Stuart M. ORCID: https://orcid.org/0000-0003-1776-7489 and Whitaker, Roger M. ORCID: https://orcid.org/0000-0002-8473-1913 2017. Reachable but not receptive: enhancing smartphone interruptibility prediction by modelling the extent of user engagement with notifications. Pervasive and Mobile Computing 40 , pp. 480-494. 10.1016/j.pmcj.2017.01.011

Preview

PDF - Accepted Post-Print Version Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (303kB) | Preview

Abstract

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.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software T Technology > T Technology (General)
Uncontrolled Keywords:	Interruptibility, notifications, human behaviour, smartphone, mobile
Publisher:	Elsevier
ISSN:	1574-1192
Date of First Compliant Deposit:	31 January 2017
Date of Acceptance:	31 January 2017
Last Modified:	09 Nov 2024 18:15
URI:	https://orca.cardiff.ac.uk/id/eprint/97910

Citation Data

Cited 33 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item