Discovering Mobile Application Usage Patterns from a Large-Scale Dataset

Abstract

The discovering of patterns regarding how, when, and where users interact with mobile applications reveals important insights for mobile service providers. In this work, we exploit for the first time a real and large-scale dataset representing the records of mobile application usage of 5,342 users during 2014. The data was collected by a software agent, installed at the users’ smartphones, which monitors detailed usage of applications. First, we look for general patterns of how users access some of the most popular mobile applications in terms of frequency, duration, diversity, and data traffic. Next, we mine the dataset looking for temporal patterns in terms of when and how often accesses occur. Finally, we exploit the location of each access to detect users’ points of interest and location-based communities. Based on the results, we derive a model to generate synthetic datasets of mobile application usage and evaluate solutions to predict the next application to be launched. We also discuss a series of implications of the findings regarding telecommunication services, mobile advertisements, and smart cities. This is the first time this dataset is used, and we also make it publicly available for other researchers.

Smartphone App Usage Analysis: Datasets, Methods, and Applications

“…Some studies looked into the temporal patterns of app sessions. Silva et al [109] conducted description statistics on app session time and discovered that map and media apps have longer app sessions. As users' activities for app advertisement are dependent on app session time [110], Rula et al [113] proposed using decision trees to predict app session time for better advertising.…”

SCOrE: um serviço de classificação de usuários móveis com base em seus aplicativos e suas cidades

“…[Do and Gatica-Perez 2010] coletam dados de 111 voluntários para identificar e prever padrões do uso de cinco tipos de aplicativos (chamada de voz, envio de mensagem, Internet, câmera e galeria). O trabalho de [Silva et al 2018] considera o uso de 8 aplicativos durante um ano, identificando padrões diferentes de frequência de uso de acordo com períodos do dia e outros contextos. [Alvarez-Lozano et al 2014] trabalham com as correlac ¸ões entre quatro categorias de aplicativos (entretenimento, social, estilo de vida e ferramenta) e distúrbios de bipolaridade de 18 pacientes de uma clínica.…”

Understanding Data Usage Patterns of Geographically Diverse Mobile Users

“…Several other studies [68], [69], [70], [10] have focussed on mobile application usage behavior and retention patterns. Silva et al [10] study mobile application usage patterns using an year-long dataset collected from devices of mobile users in Brazil. They investigate mobile application usage patterns in terms of temporal and location differences.…”

“…Understanding the data usage patterns and behavior of mobile users at different locations and market-places are paramount for service and content providers, and endusers. Mobile network operators can utilize the information to manage the increasing demand for mobile data usage [8], to plan and to optimize telecommunication resources [9], [10]. It can also be used to develop different data plan products [11] by targeting potential users.…”