Identifying diverse usage behaviors of smartphone apps

Xu, Qiang; Erman, Jeffrey; Gerber, Alexandre; Mao, Z. Morley; Pang, Jong-Shi; Venkataraman, Shobha

doi:10.1145/2068816.2068847

Cited by 347 publications

(208 citation statements)

References 21 publications

Supporting

Mentioning

202

Contrasting

Unclassified

Order By: Relevance

“…These works are different from existing work in the sense that they collect the logs from the user's smartphone and analyze the application usage behavior of individual users. On the other hand, [18] and [19] make their analysis of smartphone apps usage using anonymized datasets from Internet service providers and cellular networks, which are more diversified and abundant. [18] analyzes correlations between various parameters such as data volume, subscribers, access time, and various applications; their analysis is helpful in increasing QoS of the providers.…”

Section: Related Workmentioning

confidence: 99%

“…On the other hand, [18] and [19] make their analysis of smartphone apps usage using anonymized datasets from Internet service providers and cellular networks, which are more diversified and abundant. [18] analyzes correlations between various parameters such as data volume, subscribers, access time, and various applications; their analysis is helpful in increasing QoS of the providers. Even though the datasets used in these researches have some similarities, our work differentiates from existing literature in the sense that we focus on: 1) profiling and clustering of different mobile applications using temporal characteristics, and 2) predicting usage of an individual application at a more fine-grained scale.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Characterizing and predicting mobile application usage

Lim

Secci

Tabourier

et al. 2016

Computer Communications

View full text Add to dashboard Cite

In this paper, we propose data clustering techniques to predict temporal characteristics of data consumption behavior of different mobile applications via wireless communications. While most of the research on mobile data analytics focuses on the analysis of call data records and mobility traces, our analysis concentrates on mobile application usages, to characterize them and predict their behavior. We exploit mobile application usage logs provided by a Wi-Fi local area network service provider to characterize temporal behavior of mobile applications. More specifically, we generate daily profiles of "what" types of mobile applications users access and "when" users access them. From these profiles, we create usage classes of mobile applications via aggregation of similar profiles depending on data consumption rate, using three clustering techniques that we compare. Furthermore, we show that we can utilize these classes to analyze and predict future usages of each mobile application through progressive comparison using distance and similarity comparison techniques. Finally, we also detect and exploit outlying behavior in application usage profiles and discuss methods to efficiently predict them.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Characterizing and predicting mobile application usage

Lim

Secci

Tabourier

et al. 2016

Computer Communications

View full text Add to dashboard Cite

show abstract

“…For instance, according to [25] the top 100 applications (i.e., Google Play Store or Apple iTunes) are responsible for almost 90% of the access time and 80% of the traffic volume. In most of the cases application usage is all about the exchange of content (e.g., news, video-on-demand, emergency announcements), which in many cases can be of interest to multiple participants; e.g., updates on concurrent sports matches, departure times for public transportation after a football match.…”

Section: Related Workmentioning

confidence: 99%

On the feasibility of a user-operated mobile content distribution network

Psaras

Sourlas

Shtefan

et al. 2017

2017 IEEE 18th International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM)

View full text Add to dashboard Cite

Abstract-The vast majority of mobile data transfers today follow the traditional client-server model. Although in the fixed network P2P approaches have been exploited and shown to be very efficient, in the mobile domain there has been limited attempt to leverage on P2P (D2D) for large-scale content distribution (i.e., not DTN-like, point-to-point message transfers). In this paper, we explore the potential of a user-operated, smartphonecentric content distribution model for smartphone applications. In particular, we assume source nodes that are updated directly from the content provider (e.g., BBC, CNN), whenever updates are available; destination nodes are then directly updated by source nodes in a D2D manner. We leverage on sophisticated information-aware and application-centric connectivity techniques to distribute content between mobile devices in densely-populated urban environments. Our target is to investigate the feasibility of an opportunistic content distribution network in an attempt to achieve widespread distribution of heavy content (e.g., video files) to the majority of the destination nodes. We propose ubiCDN as a ubiquitous, user-operated and distributed CDN for mobile applications.

show abstract

“…Dicha área aborda la explicación de los eventos del ciclo de vida de las aplicaciones, a partir de la observación de diferentes tipos de información. Entre los primeros trabajos se destacan los de Bohmer [12,4,14], los cuales exploraron la relación existente entre el consumo de aplicaciones y distintas dimensiones contextuales y demográfi-cas, encontrando varios indicios de la dependencia del consumo de ciertos grupos de aplicaciones de acuerdo con las características del contexto actual del usuario. En esta línea, trabajos posteriores lograron resultados relevantes al analizar la probabilidad de la co-ocurrencia entre estados actuales de dimensiones contextuales y su influencia en el lanzamiento de aplicaciones, resaltando la utilización de información sobre el tiempo, la localización, el perfil demográfico del usuario y la última aplicación utilizada [11,5,15].…”

Section: Trabajos Relacionadosunclassified

Análisis del comportamiento contextual del usuario y su relación con el consumo de aplicaciones móviles

Rojas-Potosí

Wives

Fernández

et al. 2014

rev.ing.univ.Medellin

View full text Add to dashboard Cite

ResumenEl mercado de aplicaciones móviles crece aceleradamente, captando la atención sobre el análisis del consumo de las mismas para mejorar su recomendación y la satisfacción del usuario, soportado en la búsqueda de información que permita explicar la ocurrencia de eventos del ciclo de vida de las aplicaciones. En este sentido algunos estudios muestran una fuerte relación entre dichos eventos e información sobre la situación contextual actual del usuario y su registro de consumo de aplicaciones. Sin embargo, dichos trabajos no consideran la relación existente entre el registro de estados de las dimensiones contextuales (denominado como CUBe) y la ocurrencia de eventos del ciclo de vida de las aplicaciones, tal como lo hace este estudio. En este sentido, se presenta un análisis estadístico sobre un dataset real, evidenciando una fuerte relación entre el CUBe y el lanzamiento de un conjunto de aplicaciones. Finalmente, se describe un escenario donde estas relaciones pueden ser utilizadas para enriquecer sistemas de recomendación para aplicaciones móviles.Palabras clave: análisis contextual de comportamiento, usuario, aplicaciones móviles.

show abstract

Identifying diverse usage behaviors of smartphone apps

Cited by 347 publications

References 21 publications

Characterizing and predicting mobile application usage

Characterizing and predicting mobile application usage

On the feasibility of a user-operated mobile content distribution network

Análisis del comportamiento contextual del usuario y su relación con el consumo de aplicaciones móviles

Contact Info

Product

Resources

About