Modelling the Closed-Loop Dynamics Between a Social Media Recommender System and Users’ Opinions

Abstract

This article proposes a mathematical model to study the coupled dynamics of a recommender system (RS) algorithm and content consumers (users). The model posits that a large population of users, each with an opinion, consumes personalised content recommended by the RS. The RS can select from a range of content to recommend based on users’ past engagement, while users can engage with the content (e.g., like or watch), and in doing so, their opinions evolve. This occurs repeatedly to capture the endless content available for user consumption on social media. We employ a campaign of Monte Carlo simulations to study how RSs influence users’ opinions and, in turn, how users’ opinions shape subsequent recommended content. Both the performance of the RS (e.g., how users engage with the content) and the polarisation and radicalisation of users’ opinions are of interest. We find that different opinion distributions are more susceptible to polarisation than others, that many content stances are ineffective at changing user opinions, and that creating viral content is an effective measure for combating opinion polarisation.