# Bandits for Online Calibration: An Application to Content Moderation on Social Media Platforms

arXiv: https://arxiv.org/abs/2211.06516 · HTML: https://mlsanity.com/paper/2211.06516/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 30 references that are in the map.
- First posted on arXiv 11 Nov 2022.

## Builds on (most cited first, 6 of 6)

- [Batched Multi-armed Bandits Problem](https://mlsanity.com/paper/1904.01763/) (2019)
- [Automatic Detection of Cyberbullying in Social Media Text](https://mlsanity.com/paper/1801.05617/) (2018)
- [Preserving Integrity in Online Social Networks](https://mlsanity.com/paper/2009.10311/) (2020)
- [Detection of Cyberbullying Incidents on the Instagram Social Network](https://mlsanity.com/paper/1503.03909/) (2015)
- [TIES: Temporal Interaction Embeddings For Enhancing Social Media Integrity At Facebook](https://mlsanity.com/paper/2002.07917/) (2020)
- [Popularity Prediction for Social Media over Arbitrary Time Horizons](https://mlsanity.com/paper/2009.02092/) (2020)

## Built on by (most cited first, 6 of 6)

- [HateDay: Insights from a Global Hate Speech Dataset Representative of a Day on Twitter](https://mlsanity.com/paper/2411.15462/) (2024)
- [On the Importance of Uncertainty in Decision-Making with Large Language Models](https://mlsanity.com/paper/2404.02649/) (2024)
- [Active Human Feedback Collection via Neural Contextual Dueling Bandits](https://mlsanity.com/paper/2504.12016/) (2025)
- [The Enforcement and Feasibility of Hate Speech Moderation](https://mlsanity.com/paper/2604.12289/) (2026)
- [Reinforcement Learning for Efficient Toxicity Detection in Competitive Online Video Games](https://mlsanity.com/paper/2503.20968/) (2025)
- [Optimality of Sub-network Laplace Approximations: New Results and Methods](https://mlsanity.com/paper/2605.09075/) (2026)

## Abstract (arXiv)

We describe the current content moderation strategy employed by Meta to remove policy-violating content from its platforms. Meta relies on both handcrafted and learned risk models to flag potentially violating content for human review. Our approach aggregates these risk models into a single ranking score, calibrating them to prioritize more reliable risk models. A key challenge is that violation trends change over time, affecting which risk models are most reliable. Our system additionally handles production challenges such as changing risk models and novel risk models. We use a contextual bandit to update the calibration in response to such trends. Our approach increases Meta's top-line metric for measuring the effectiveness of its content moderation strategy by 13%.