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

arXiv: https://arxiv.org/abs/2305.16941 · HTML: https://mlsanity.com/paper/2305.16941/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 May 2023.

## Built on by (most cited first, 30 of 30)

- [Visibility into AI Agents](https://mlsanity.com/paper/2401.13138/) (2024)
- [AI Alignment with Changing and Influenceable Reward Functions](https://mlsanity.com/paper/2405.17713/) (2024)
- [How malicious AI swarms can threaten democracy: The fusion of agentic AI and LLMs marks a new frontier in information warfare](https://mlsanity.com/paper/2506.06299/) (2025)
- [HateDay: Insights from a Global Hate Speech Dataset Representative of a Day on Twitter](https://mlsanity.com/paper/2411.15462/) (2024)
- [Meaning Is Not A Metric: Using LLMs to make cultural context legible at scale](https://mlsanity.com/paper/2505.23785/) (2025)
- [Agents in the Wild: Safety, Society, and the Illusion of Sociality on Moltbook](https://mlsanity.com/paper/2602.13284/) (2026)
- [Position: Anthropomorphic Misalignment Research Needs Stronger Evidence](https://mlsanity.com/paper/2606.07612/) (2026)
- [Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value](https://mlsanity.com/paper/2512.03399/) (2025)
- [Value Alignment of Social Media Ranking Algorithms](https://mlsanity.com/paper/2509.14434/) (2025)
- [CTRL-Rec: Controlling Recommender Systems With Natural Language](https://mlsanity.com/paper/2510.12742/) (2025)
- [LLMs Can Get "Brain Rot": A Pilot Study on Twitter/X](https://mlsanity.com/paper/2510.13928/) (2025)
- [Dynamics of Algorithmic Content Amplification on TikTok](https://mlsanity.com/paper/2503.20231/) (2025)
- [The Problem of Algorithmic Collisions: Mitigating Unforeseen Risks in a Connected World](https://mlsanity.com/paper/2505.20181/) (2025)
- [Large Language Models, and LLM-Based Agents, Should Be Used to Enhance the Digital Public Sphere](https://mlsanity.com/paper/2410.12123/) (2024)
- [The Enforcement and Feasibility of Hate Speech Moderation](https://mlsanity.com/paper/2604.12289/) (2026)
- [How AI Writing Assistance Distorts Perceptions of AI Users and Their Opinions](https://mlsanity.com/paper/2604.22503/) (2026)
- [Solipsistic Superintelligence is Unlikely to be Cooperative](https://mlsanity.com/paper/2606.03237/) (2026)
- [Responsiveness Verification: Will Predictions Change? How Much? How Often?](https://mlsanity.com/paper/2507.02169/) (2025)
- [Measuring Narrative Polarization in Online Discourse](https://mlsanity.com/paper/2601.07398/) (2026)
- [Ideological Isolation in Online Social Networks: A Survey of Computational Definitions, Metrics, and Mitigation Strategies](https://mlsanity.com/paper/2601.07884/) (2026)
- [When Nobody Around Is Real: Exploring Public Opinions and User Experiences On the Multi-Agent AI Social Platform](https://mlsanity.com/paper/2601.18275/) (2026)
- [Recommender system in X inadvertently profiles ideological positions of users](https://mlsanity.com/paper/2602.02624/) (2026)
- [LLM Active Alignment: A Nash Equilibrium Perspective](https://mlsanity.com/paper/2602.06836/) (2026)
- [Stability Regimes for Framing-Sensitive Fine-Tuning in Language Models](https://mlsanity.com/paper/2602.15273/) (2026)
- [Attention Asymmetry in AI Layoff Discourse on X: A Computational Analysis of Capital vs Labour Amplification](https://mlsanity.com/paper/2605.29367/) (2026)
- [LLM-Assisted Reranking to Operationalize Nuanced Objectives in Recommender Systems](https://mlsanity.com/paper/2606.02883/) (2026)
- [Position: AI Must Become Planet-Centered, Not Just Human-Centered](https://mlsanity.com/paper/2606.13704/) (2026)
- [Using AI Agents to Automate Black-Box Audits of Personalization Algorithms at Scale](https://mlsanity.com/paper/2606.30801/) (2026)
- [Contagion on the Trading Floor: How Adversarial Signals Spread in Multi-Agent Trading Systems](https://mlsanity.com/paper/2609.19789/) (2026)
- [Agent-based Modeling: Equilibrium, Echo Chambers, and Efficiency in Hybrid Coevolutionary Opinion Games](https://mlsanity.com/paper/2609.27639/) (2026)

## Abstract (arXiv)

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 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.