# Designing Recommender Systems to Depolarize

arXiv: https://arxiv.org/abs/2107.04953 · HTML: https://mlsanity.com/paper/2107.04953/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jul 2021.

## Built on by (most cited first, 11 of 11)

- [Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems](https://mlsanity.com/paper/2405.06624/) (2024)
- [Estimating and Penalizing Induced Preference Shifts in Recommender Systems](https://mlsanity.com/paper/2204.11966/) (2022)
- [Reranking partisan animosity in algorithmic social media feeds alters affective polarization](https://mlsanity.com/paper/2411.14652/) (2024)
- [AI and the Future of Digital Public Squares](https://mlsanity.com/paper/2412.09988/) (2024)
- [Manifestations of Xenophobia in AI Systems](https://mlsanity.com/paper/2212.07877/) (2022)
- [Recommender Systems for Good (RS4Good): Survey of Use Cases and a Call to Action for Research that Matters](https://mlsanity.com/paper/2411.16645/) (2024)
- [Measuring and Controlling Divisiveness in Rank Aggregation](https://mlsanity.com/paper/2306.08511/) (2023)
- [Content-Agnostic Moderation for Stance-Neutral Recommendation](https://mlsanity.com/paper/2405.18941/) (2024)
- [Explicit User Manipulation in Reinforcement Learning Based Recommender Systems](https://mlsanity.com/paper/2203.10629/) (2022)
- [All Polarized but Still Different: a Multi-factorial Metric to Discriminate between Polarization Behaviors on Social Media](https://mlsanity.com/paper/2312.04603/) (2023)
- [LLM-Assisted Reranking to Operationalize Nuanced Objectives in Recommender Systems](https://mlsanity.com/paper/2606.02883/) (2026)

## Abstract (arXiv)

Polarization is implicated in the erosion of democracy and the progression to violence, which makes the polarization properties of large algorithmic content selection systems (recommender systems) a matter of concern for peace and security. While algorithm-driven social media does not seem to be a primary driver of polarization at the country level, it could be a useful intervention point in polarized societies. This paper examines algorithmic depolarization interventions with the goal of conflict transformation: not suppressing or eliminating conflict but moving towards more constructive conflict. Algorithmic intervention is considered at three stages: which content is available (moderation), how content is selected and personalized (ranking), and content presentation and controls (user interface). Empirical studies of online conflict suggest that the exposure diversity intervention proposed as an antidote to "filter bubbles" can be improved and can even worsen polarization under some conditions. Using civility metrics in conjunction with diversity in content selection may be more effective. However, diversity-based interventions have not been tested at scale and may not work in the diverse and dynamic contexts of real platforms. Instead, intervening in platform polarization dynamics will likely require continuous monitoring of polarization metrics, such as the widely used "feeling thermometer." These metrics can be used to evaluate product features, and potentially engineered as algorithmic objectives. It may further prove necessary to include polarization measures in the objective functions of recommender algorithms to prevent optimization processes from creating conflict as a side effect.