Mobile application usage prediction through context-based learning

Abstract

The purchase and download of new applications on all types of smartphones and tablet computers has become increasingly popular. On each mobile device, many applications are installed, often resulting in crowded icon-based interfaces. In this paper, we present a framework for the prediction of a user's future mobile application usage behavior. On the mobile device, the framework continuously monitors the user's previous use of applications together with several context parameters such as speed and location. Based on the retrieved information, the framework automatically deduces application usage patterns. These patterns define a correlation between a used application and the monitored context information or between different applications. Furthermore, by combining several context parameters, context profiles are automatically generated. These profiles typically match with real life situations such as 'at home' or 'on the train' and are used to delimit the number of possible patterns, increasing both the positive prediction rate and the scalability of the system. A concept demonstrator for Android OS was developed and the implemented algorithms were evaluated in a detailed simulation setup. It is shown that the developed algorithms perform very well with a true positive rate of up to 90% for the considered evaluation scenarios.

Detecting Drinking Episodes in Young Adults Using Smartphone-based Sensors

“…In the field of ubiquitous computing, smartphone instrumentation has enabled better understanding of users' interaction with these devices in specific contexts. For example, they have increased our understanding of how people use applications [3,22] and smartphone networks [23], and allowed us to predict which application is relevant to the current context [35,50], and to detect the most opportune moments to deliver information to users [32]. More related to our work, in the area of health and wellbeing, the widespread availability of smartphones in today's young adult population has prompted research that leverages the embedded sensors in smartphones to study human behavior.…”

“…(a) ESM reports across the participants (n=38) including excluded participants(31)(32)(33)(34)(35)(36)(37)(38) (b) Drinking reports per each participant (n=30): x-axis refers to days during the study (max=28 days), y-axis refers to the number of standard alcohol drinks consumed ESM reports of drinking episodes for each participant.…”

Demographics of mobile app usage: long-term analysis of mobile app usage

“…Tu et al [61] measured the uniqueness of mobile app usage behavior considering spatial and temporal context information. Other works [20,24,32,35,55] focused more on the prediction of app usage by studying how to predict which apps users are likely to install or visit. Xu et al [64] identified traffic from distinct marketplace apps and presented statistic results on their spatio-temporal prevalence and correlation.…”

Revisitation analysis of smartphone app use

“…Leroux et al developed a mobile framework that creates context profiles by monitoring application use, day of week, and the user's speed and location [18]. Although using artificially created data, the resulting profiles match real life situations, such as "at work" or "commuting," and can be used to infer a set of applications the user is likely to use.…”