Predicting user traits from a snapshot of apps installed on a smartphone

Third party apps are an integral component of the smartphone ecosystem. In this paper, we investigate how user traits can be inferred by observing only a single snapshot of installed apps. Using supervised learning methods and minimal external information we show that user traits such as religion, relationship status, spoken languages, countries of interest, and whether or not the user is a parent of small children, can be easily predicted. Using data collected from over 200 smartphone users, specifically the list of installed apps and the corresponding ground truth traits of the users, we show that for most traits we can achieve over 90% precision. Our inference method can be used to provide services such as personalized content delivery or recommender systems for users. We also highlight privacy loss that can occur from unrestricted access to the app lists in popular smartphone operating systems.

[1]  Hua Li,et al.  Demographic prediction based on user's browsing behavior , 2007, WWW '07.

[2]  T. Graepel,et al.  Private traits and attributes are predictable from digital records of human behavior , 2013, Proceedings of the National Academy of Sciences.

[3]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[4]  Johannes Schöning,et al.  Falling asleep with Angry Birds, Facebook and Kindle: a large scale study on mobile application usage , 2011, Mobile HCI.

[5]  Jie Liu,et al.  Fast app launching for mobile devices using predictive user context , 2012, MobiSys '12.

[6]  Alex Pentland,et al.  Composite Social Network for Predicting Mobile Apps Installation , 2011, AAAI.

[7]  Ye Xu,et al.  Preference, context and communities: a multi-faceted approach to predicting smartphone app usage patterns , 2013, ISWC '13.

[8]  Shashi Shekhar,et al.  AdSplit: Separating Smartphone Advertising from Applications , 2012, USENIX Security Symposium.

[9]  Yiming Yang,et al.  A Comparative Study on Feature Selection in Text Categorization , 1997, ICML.

[10]  Daniel Gatica-Perez,et al.  Who's Who with Big-Five: Analyzing and Classifying Personality Traits with Smartphones , 2011, 2011 15th Annual International Symposium on Wearable Computers.

[11]  R. Bennett.  What a Difference a Year Makes , 2006, Care Management Journals.

[12]  Yunxin Liu,et al.  MoodScope: building a mood sensor from smartphone usage patterns , 2013, MobiSys.

[13]  David Chu,et al.  Practical prediction and prefetch for faster access to applications on mobile phones , 2013, UbiComp.

[14]  Malik Yousef,et al.  One-Class SVMs for Document Classification , 2002, J. Mach. Learn. Res..

[15]  Clayton Shepard,et al.  LiveLab: measuring wireless networks and smartphone users in the field , 2011, SIGMETRICS Perform. Evaluation Rev..

[16]  Xuxian Jiang,et al.  Unsafe exposure analysis of mobile in-app advertisements , 2012, WISEC '12.

[17]  Sharad Goel,et al.  Who Does What on the Web: A Large-Scale Study of Browsing Behavior , 2012, ICWSM.

[18]  Cecilia Mascolo,et al.  Don't kill my ads!: balancing privacy in an ad-supported mobile application market , 2012, HotMobile '12.

[19]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.