Abstract:
|
With the increasing abundance of `digital footprints' left by human interactions in online environments, e.g. through social media and app use, the ability to model such behavior has become increasingly possible. Many approaches have been proposed, such as renewal process models, however, most previous model frameworks are typically restrictive, and often the models are not directly compared on a diverse collection of human behavior. In this work, we seek to address these shortcomings. We develop three non-parametric models for exogenously-driven, self-driven, and socially-driven behavior in digital social networks, and compare their predictive and descriptive abilities on a heterogeneous catalog of human behavior collected from fifteen thousand users on the microblogging platform Twitter over the course of a year. We find that despite the popularity of renewal processes for explaining digitally-mediated human behavior, most users are better modeled as self- or socially-driven. Our work highlights the importance of a flexible modeling approach when attempting to explain and predict human behavior in digital environments.
|