Mining and Predicting Smart Device User Behavior

Three types of user behavior are mined in this paper: application usage, smart device usage and periodicity of user behavior. When mining application usage, the application installation, most frequently used applications and application correlation are analyzed. The application usage is long-tailed. When mining the device usage, the mean, variance and autocorrelation are calculated both for duration and interval. Both the duration and interval are long-tailed but only duration satisfies power-law distribution. Meanwhile, the autocorrelation of both duration and interval is weak, which makes predicting user behavior based on adjacent behavior not so reasonable in related works. Then DFT (Discrete Fourier Transform) is utilized to analyze the periodicity of user behavior and results show that the most obvious periodicity is 24 hours, which is in agreement with related works. Based on the results above, an improved user behavior predicting model is proposed based on Chebyshev inequality. Experiment results show that the performance is good in accurate rate and recall rate.

[1]  Guodong Sun,et al.  Daily Mood Assessment Based on Mobile Phone Sensing , 2012, 2012 Ninth International Conference on Wearable and Implantable Body Sensor Networks.

[2]  Wang-Chien Lee,et al.  App recommendation: a contest between satisfaction and temptation , 2013, WSDM.

[3]  Wen-Chih Peng,et al.  Mining Temporal Profiles of Mobile Applications for Usage Prediction , 2012, 2012 IEEE 12th International Conference on Data Mining Workshops.

[4]  Kenneth C. C. Yang,et al.  Exploring factors affecting the adoption of mobile commerce in Singapore , 2005, Telematics Informatics.

[5]  Lai Tu,et al.  We Know What You Are--A User Classification Based on Mobile Data , 2013, 2013 IEEE International Conference on Green Computing and Communications and IEEE Internet of Things and IEEE Cyber, Physical and Social Computing.

[6]  Ming Zhang,et al.  Where is the energy spent inside my app?: fine grained energy accounting on smartphones with Eprof , 2012, EuroSys '12.

[7]  Xiaoxiao Ma,et al.  Predicting mobile application usage using contextual information , 2012, UbiComp.

[8]  Guanling Chen,et al.  AppJoy: personalized mobile application discovery , 2011, MobiSys '11.

[9]  Wang Bing-hong.  Statistical Physics Research for Human Behaviors,Complex Networks,and Information Mining , 2012 .

[10]  Philip S. Yu,et al.  Mining Cluster-Based Temporal Mobile Sequential Patterns in Location-Based Service Environments , 2011, IEEE Transactions on Knowledge and Data Engineering.

[11]  Tsvi Kuflik,et al.  Functionality-based clustering using short textual description: helping users to find apps installed on their mobile device , 2013, IUI '13.

[12]  Jin-Hyuk Hong,et al.  Understanding and prediction of mobile application usage for smart phones , 2012, UbiComp.