The Impact of Curation Algorithms on Social Network Content Quality and Structure

Abstract

Curation algorithms are selection and ranking algorithms on social media that help consumers experience better content. These algorithms have been blamed in the past few years for the creation of “filter bubbles” and other phenomena in social media. We analyze a platform with producers and consumers of content to understand the impact of curation algorithms on the amount of friends each consumer has and the quality of content created by each producer. Our model takes into account both vertical and horizontal differentiation and analyzes three different types of algorithms.We find that without algorithmic curation, the number of friends a consumer has and the quality of content on the platform are strategic complements. When algorithmic curation is introduced, the resulting process makes consumers less selective in their choice of whom to follow. In equilibrium, producers of content receive lower payoffs because they enter into a prisoner’s dilemma like contest. The quality of content on the platform may increase if the marginal cost of producing this quality is high enough but not too high. Both of these effects may result theoretically in more diverse content consumed by consumers, but in equilibrium we find that a few of the algorithms may reduce the horizontal distance of matched content, which may result in a filter bubble. We identify an algorithm that focuses on filtering low quality items that results in higher quality of content as well as higher diversity under specific conditions.