WhatsApp Usage Patterns and Prediction Models

This paper presents an extensive study of the usage of the WhatsApp social network, an Internet messaging application that is quickly replacing SMS messaging. It is based on the analysis of over 4 million messages from nearly 100 users that we collected in order to understand people’s use of the network. We believe that this is the first in-depth study of the properties of WhatsApp messages with an emphasis of noting differences across different age and gender demographic groups. It is also the first to use statistical and data analytic tools in this analysis. We found that different genders and age demographics had significantly different usage habits in almost all message and group attributes. These differences facilitate the development of user prediction models based on data mining tools. We illustrate this by developing several prediction models such as for a person’s gender or approximate age. We also noted differences in users’ group behavior. We created group behaviorial models including the likelihood a given group would have more file attachments, if a group would contain a larger number of participants, a higher frequency of activity, quicker response times and shorter messages. We present a detailed discussion about the specific attributes that were contained in all predictive models and suggest possible applications based on these results.

[1]  Lada A. Adamic,et al.  The role of social networks in information diffusion , 2012, WWW.

[2]  Robert E. Kraut,et al.  Gender, topic, and audience response: an analysis of user-generated content on facebook , 2013, CHI.

[3]  Pedro Casas,et al.  Vivisecting whatsapp through large-scale measurements in mobile networks , 2014, SIGCOMM.

[4]  Shlomo Argamon,et al.  Automatically profiling the author of an anonymous text , 2009, CACM.

[5]  C. Montag,et al.  Smartphone usage in the 21st century: who is active on WhatsApp? , 2015, BMC Research Notes.

[6]  Yang-Han Lee,et al.  Time distortion associated with smartphone addiction: Identifying smartphone addiction via a mobile application (App). , 2015, Journal of psychiatric research.

[7]  Nimmi Rangaswamy,et al.  Offline Strangers, Online Friends: Bridging Classroom Gender Segregation with WhatsApp , 2015, CHI.

[8]  David García,et al.  It's a Man's Wikipedia? Assessing Gender Inequality in an Online Encyclopedia , 2015, ICWSM.

[9]  M. Thelwall,et al.  Data mining emotion in social network communication: Gender differences in MySpace , 2010 .

[10]  Martin Pielot,et al.  Didn't you see my message?: predicting attentiveness to mobile instant messages , 2014, CHI.

[11]  Jennifer Neville,et al.  Modeling relationship strength in online social networks , 2010, WWW '10.

[12]  Thomas Gottron,et al.  Bad news travel fast: a content-based analysis of interestingness on Twitter , 2011, WebSci '11.

[13]  J. Ross Quinlan,et al.  Improved Use of Continuous Attributes in C4.5 , 1996, J. Artif. Intell. Res..

[14]  Kenton O'Hara,et al.  Everyday dwelling with WhatsApp , 2014, CSCW.

[15]  A. Darzi,et al.  Smartphones let surgeons know WhatsApp: an analysis of communication in emergency surgical teams. , 2015, American Journal of Surgery.

[16]  A. Kring,et al.  Sex differences in emotion: expression, experience, and physiology. , 1998, Journal of personality and social psychology.

[17]  Rodrigo de Oliveira,et al.  What's up with whatsapp?: comparing mobile instant messaging behaviors with traditional SMS , 2013, MobileHCI '13.

[18]  Dan Bouhnik,et al.  WhatsApp Goes to School: Mobile Instant Messaging between Teachers and Students , 2014, J. Inf. Technol. Educ. Res..