PrefMiner: Mining User’s Preferences for Intelligent Mobile Notification Management

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Authors

Colleges, School and Institutes

External organisations

  • University College London

Abstract

Mobile notifications are increasingly used by a variety of applications to inform users about events, news or just to send alerts and reminders to them. However, many notifications are neither useful nor relevant to users’ interests and, also
for this reason, they are considered disruptive and potentially annoying.

In this paper we present the design, implementation and evaluation of PrefMiner, a novel interruptibility management solution that learns users’ preferences for receiving notifications based on automatic extraction of rules by mining their interaction with mobile phones. The goal is to build a system that is intelligible for users, i.e., not just a “black-box” solution. Rules are shown to users who might decide to accept or discard them at run-time. The design of PrefMiner is based on a large scale mobile notification dataset and its effectiveness is evaluated by means of an in-the-wild deployment.

Details

Original languageEnglish
Title of host publicationProceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp 2016)
Publication statusPublished - 17 Sep 2016
Event2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp 2016) - Heidelberg, Germany
Duration: 12 Sep 201616 Sep 2016

Conference

Conference2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp 2016)
CountryGermany
CityHeidelberg
Period12/09/1616/09/16