Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
PrefMiner: mining user’s preferences for intelligent mobile notification management
Mehrotra A., Hendley R., Musolesi M.  UbiComp 2016 (Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, Heidelberg, Germany, Sep 12-16, 2016)1223-1234.2016.Type:Proceedings
Date Reviewed: Jun 1 2017

Mehrotra et al. present PrefMiner, a novel notification interruptibility management system that filters notifications according to user preferences. PrefMiner delivers only useful notifications to users at opportune moments. PrefMiner learns users’ preferences for receiving notifications. It is built on top of MyPref library, a lightweight Android interruptibility management library that can predict notifications regarding user preferences.

The novelty of this study relies on the ability of PrefMiner to learn user preferences, while common systems use context and content to predict opportune moments for notification delivery. Notifications that arrive at inopportune moments are not considered by existing systems. Furthermore, they present limitations (for example, users do not understand the models of these systems, or users cannot provide feedback) that PrefMiner overcomes. PrefMiner enables users to adjust the interruptibility management mechanism to best manage the interruption.

The authors discuss how to extract notifications rules and classify the notifications. Notifications such as battery status, alarm, and calendar events are classified as reminders. The authors launch a novel notifications classification that clusters the notifications based on the notification title instead of categorizing the notifications based on type of applications that generate them. The authors also present the construction of association rules about users’ preferences. An association rule represents an antecedent and its consequent.

Five association rules are constructed and a set of static notifications to evaluate mechanisms is used. The overall result of the evaluation, using online learning methods, shows that the prediction accuracy of association rules depends on the amount of available notifications. Additionally, the MyPref library is also evaluated. The results show that the energy consumption and the time complexity linearly increase as the notification amount increases.

This paper presents a novelty in the field of notification management. I recommend it.

Reviewer:  Thierry Edoh Review #: CR145314 (1708-0552)
Bookmark and Share
  Featured Reviewer  
 
User/ Machine Systems (H.1.2 )
 
 
User Interfaces (H.5.2 )
 
Would you recommend this review?
yes
no
Other reviews under "User/Machine Systems": Date
The future of interactive systems and the emergence of direct manipulation
Shneiderman B.  Human factors and interactive computer systems (, New York,281984. Type: Proceedings
May 1 1985
Reading continuous text from a one-line visual display
Monk A. International Journal of Man-Machine Studies 21(3): 269-277, 1984. Type: Article
Oct 1 1985
Readings on cognitive ergonomics - mind and computers
van der Veer G., Tauber M. (ed), Green T. (ed), Gorny P. (ed)  Readings on cognitive ergonomics - mind and computers,Gmunden, Austria,1984. Type: Whole Proceedings
May 1 1986
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2024 ThinkLoud®
Terms of Use
| Privacy Policy