Interpretable Machine Learning for Mobile Notification Management: An Overview of PrefMiner

Abhinav Mehrotra, Robert Hendley, Mirco Musolesi

Research output: Contribution to journalArticlepeer-review

135 Downloads (Pure)

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, for this reason, they are considered disruptive and potentially annoying, as well. PrefMiner is 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. PrefMiner aims at being intelligible and interpretable for users, i.e., not just a “black box” solution, by suggesting rules 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.
Original languageEnglish
Pages (from-to)35-38
JournalGetMobile: Mobile Computing and Communications
Volume21
Issue number2
DOIs
Publication statusPublished - 30 Jun 2017

Fingerprint

Dive into the research topics of 'Interpretable Machine Learning for Mobile Notification Management: An Overview of PrefMiner'. Together they form a unique fingerprint.

Cite this