A computational reward learning account of social media engagement

This paper investigates whether reward learning mechanisms contribute to social media behavior. Using computational models based on reinforcement learning theory and analyzing over one million posts from over 4000 individuals on multiple social media platforms, the study finds that human behavior on social media conforms to reward learning principles. Users spaced their posts to maximize social rewards, considering effort and opportunity costs. Individual differences in social reward learning were also observed. An online experiment further verified the causal influence of social rewards on behavior. The findings support a reward learning account of social media engagement.

Björn Lindström, Martin Bellander, David T. Schultner, Allen Chang, Philippe N. Tobler, David M. Amodio