Designing content-driven intelligent notification mechanisms for mobile applications

TLDR

Smartphone notifications frequently arrive at inappropriate times or with irrelevant content, increasing user distraction. The study investigates how notification content, sender, and context affect mobile user interruptibility. The authors collected ~70,000 notifications from 35 users, grouped them by app and sender relationship, and built classifiers that use content and user activity to predict the optimal delivery moment. The classifiers outperformed user-defined interruptibility rules in predicting when users can be interrupted.

Abstract

An increasing number of notifications demanding the smartphone user's attention, often arrive at an inappropriate moment, or carry irrelevant content. In this paper we present a study of mobile user interruptibility with respect to notification content, its sender, and the context in which a notification is received. In a real-world study we collect around 70,000 instances of notifications from 35 users. We group notifications according to the applications that initiated them, and the social relationship between the sender and the receiver. Then, by considering both content and context information, such as the current activity of a user, we discuss the design of classifiers for learning the most opportune moment for the delivery of a notification carrying a specific type of information. Our results show that such classifiers lead to a more accurate prediction of users' interruptibility than an alternative approach based on user-defined rules of their own interruptibility.