Engagement, User Satisfaction, and the Amplification of Divisive Content on Social Media

TL;DR

This study audits Twitter's engagement-based ranking algorithm, revealing it amplifies divisive content and underperforms in user satisfaction, suggesting the need for more balanced content ranking methods.

Contribution

It provides empirical evidence that engagement-based algorithms amplify divisive content and underperform in user satisfaction, proposing alternative ranking approaches based on user preferences.

Findings

Engagement-based ranking amplifies emotionally charged, divisive content.

Users prefer content ranked by their stated preferences over engagement-based ranking.

Alternative ranking reduces hostile content but may reinforce existing biases.

Abstract

In a pre-registered algorithmic audit, we found that, relative to a reverse-chronological baseline, Twitter's engagement-based ranking algorithm amplifies emotionally charged, out-group hostile content that users say makes them feel worse about their political out-group. Furthermore, we find that users do \emph{not} prefer the political tweets selected by the algorithm, suggesting that the engagement-based algorithm underperforms in satisfying users' stated preferences. Finally, we explore the implications of an alternative approach that ranks content based on users' stated preferences and find a reduction in angry, partisan, and out-group hostile content, but also a potential reinforcement of pro-attitudinal content. The evidence underscores the necessity for a more nuanced approach to content ranking that balances engagement and users' stated preferences.