Predicting Interruptibility for Manual Data Collection: A Cluster-Based User Model (bibtex)
by Visuri, Aku, van Berkel, Niels, Goncalves, Jorge, Luo, Chu, Ferreira, Denzil and Kostakos, Vassilis
Abstract:
Previous work suggests that Quantified-Self applications can retain long-term usage with motivational methods. These methods often require intermittent attention requests with manual data input. This may cause unnecessary burden to the user, leading to annoyance, frustration and possible application abandonment. We designed a novel method that uses on-screen alert dialogs to transform recurrent smartphone usage sessions into moments of data contributions and evaluate how accurately machine learning can reduce unintended interruptions. We collected sensor data from 48 participants during a 4-week long deployment and analysed how personal device usage can be considered in scheduling data inputs. We show that up to 81.7% of user interactions with the alert dialogs can be accurately predicted using user clusters, and up to 75.5% of unintended interruptions can be prevented and rescheduled. Our approach can be leveraged by applications that require selfreports on a frequent basis and may provide a better longitudinal QS experience.
Reference:
A. Visuri, N. van Berkel, J. Goncalves, C. Luo, D. Ferreira, V. Kostakos, "Predicting Interruptibility for Manual Data Collection: A Cluster-Based User Model", in Proceedings of the International Conference on Human-Computer Interaction with Mobile Devices and Services (MobileHCI'17), 2017, Article 12.
Bibtex Entry:
@inproceedings{Visuri2017PredictingInterruptibility,
	Abstract = {Previous work suggests that Quantified-Self applications can retain long-term usage with motivational methods. These methods often require intermittent attention requests with manual data input. This may cause unnecessary burden to the user, leading to annoyance, frustration and possible application abandonment. We designed a novel method that uses on-screen alert dialogs to transform recurrent smartphone usage sessions into moments of data contributions and evaluate how accurately machine learning can reduce unintended interruptions. We collected sensor data from 48 participants during a 4-week long deployment and analysed how personal device usage can be considered in scheduling data inputs. We show that up to 81.7% of user interactions with the alert dialogs can be accurately predicted using user clusters, and up to 75.5% of unintended interruptions can be prevented and rescheduled. Our approach can be leveraged by applications that require selfreports on a frequent basis and may provide a better longitudinal QS experience.},
	Author = {Visuri, Aku and van Berkel, Niels and Goncalves, Jorge and Luo, Chu and Ferreira, Denzil and Kostakos, Vassilis},
	Booktitle = {Proceedings of the International Conference on Human-Computer Interaction with Mobile Devices and Services},
	Doi = {10.1145/3098279.3098532},
	Location = {MobileHCI'17},
	Pages = {Article 12},
	Title = {Predicting Interruptibility for Manual Data Collection: A Cluster-Based User Model},
	Type = {Conference Paper},
	Url = {https://www.nielsvanberkel.com/files/publications/mobilehci17a.pdf},
	Year = {2017}}
Powered by bibtexbrowser