# Datasets for Navigating Sensitive Topics in Recommendation Systems

arXiv: https://arxiv.org/abs/2509.07269 · HTML: https://mlsanity.com/paper/2509.07269/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 57 references that are in the map.
- First posted on arXiv 8 Sep 2025.

## Builds on (most cited first, 21 of 21)

- [Bias and Debias in Recommender System: A Survey and Future Directions](https://mlsanity.com/paper/2010.03240/) (2020)
- [Ex Machina: Personal Attacks Seen at Scale](https://mlsanity.com/paper/1610.08914/) (2016)
- [Directions in Abusive Language Training Data: Garbage In, Garbage Out](https://mlsanity.com/paper/2004.01670/) (2020)
- [Sociotechnical Harms of Algorithmic Systems: Scoping a Taxonomy for Harm Reduction](https://mlsanity.com/paper/2210.05791/) (2022)
- [MuMiN: A Large-Scale Multilingual Multimodal Fact-Checked Misinformation Social Network Dataset](https://mlsanity.com/paper/2202.11684/) (2022)
- [Auditing Radicalization Pathways on YouTube](https://mlsanity.com/paper/1908.08313/) (2019)
- [Algorithmic Amplification of Politics on Twitter](https://mlsanity.com/paper/2110.11010/) (2021)
- [Exploring Author Gender in Book Rating and Recommendation](https://mlsanity.com/paper/1808.07586/) (2018)
- [Recommendations and User Agency: The Reachability of Collaboratively-Filtered Information](https://mlsanity.com/paper/1912.10068/) (2019)
- [YouNICon: YouTube's CommuNIty of Conspiracy Videos](https://mlsanity.com/paper/2304.05274/) (2023)
- [Crank up the volume: preference bias amplification in collaborative recommendation](https://mlsanity.com/paper/1909.06362/) (2019)
- [Exploring Artist Gender Bias in Music Recommendation](https://mlsanity.com/paper/2009.01715/) (2020)
- [The Stereotyping Problem in Collaboratively Filtered Recommender Systems](https://mlsanity.com/paper/2106.12622/) (2021)
- [The Impact of Popularity Bias on Fairness and Calibration in Recommendation](https://mlsanity.com/paper/1910.05755/) (2019)
- [A Longitudinal Analysis of YouTube's Promotion of Conspiracy Videos](https://mlsanity.com/paper/2003.03318/) (2020)
- [Quantifying Availability and Discovery in Recommender Systems via Stochastic Reachability](https://mlsanity.com/paper/2107.00833/) (2021)
- [Recommender Systems and Algorithmic Hate](https://mlsanity.com/paper/2209.02159/) (2022)
- [Harm Mitigation in Recommender Systems under User Preference Dynamics](https://mlsanity.com/paper/2406.09882/) (2024)
- [Analysing the Effect of Recommendation Algorithms on the Amplification of Misinformation](https://mlsanity.com/paper/2103.14748/) (2021)
- [The dangers in algorithms learning humans' values and irrationalities](https://mlsanity.com/paper/2202.13985/) (2022)
- [Improving Collaborative Filtering based Recommenders using Topic Modelling](https://mlsanity.com/paper/1402.6238/) (2014)

## Built on by (most cited first, 2 of 2)

- [SteerEval: A Framework for Evaluating Steerability with Natural Language Profiles for Recommendation](https://mlsanity.com/paper/2601.21105/) (2026)
- [SafeCRS: Personalized Safety Alignment for LLM-Based Conversational Recommender Systems](https://mlsanity.com/paper/2603.03536/) (2026)

## Abstract (arXiv)

Personalized AI systems, from recommendation systems to chatbots, are a prevalent method for distributing content to users based on their learned preferences. However, there is growing concern about the adverse effects of these systems, including their potential tendency to expose users to sensitive or harmful material, negatively impacting overall well-being. To address this concern quantitatively, it is necessary to create datasets with relevant sensitivity labels for content, enabling researchers to evaluate personalized systems beyond mere engagement metrics. To this end, we introduce two novel datasets that include a taxonomy of sensitivity labels alongside user-content ratings: one that integrates MovieLens rating data with content warnings from the Does the Dog Die? community ratings website, and another that combines fan-fiction interaction data and user-generated warnings from Archive of Our Own.