# Reducing Unintended Identity Bias in Russian Hate Speech Detection

arXiv: https://arxiv.org/abs/2010.11666 · HTML: https://mlsanity.com/paper/2010.11666/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Oct 2020.

## Built on by (most cited first, 10 of 10)

- [Countering Online Hate Speech: An NLP Perspective](https://mlsanity.com/paper/2109.02941/) (2021)
- [Detecting Unintended Social Bias in Toxic Language Datasets](https://mlsanity.com/paper/2210.11762/) (2022)
- [Examining Temporal Bias in Abusive Language Detection](https://mlsanity.com/paper/2309.14146/) (2023)
- [RuBia: A Russian Language Bias Detection Dataset](https://mlsanity.com/paper/2403.17553/) (2024)
- [Russian Texts Detoxification with Levenshtein Editing](https://mlsanity.com/paper/2204.13638/) (2022)
- [Evolving Hate Speech Online: An Adaptive Framework for Detection and Mitigation](https://mlsanity.com/paper/2502.10921/) (2025)
- [HatePRISM: Policies, Platforms, and Research Integration. Advancing NLP for Hate Speech Proactive Mitigation](https://mlsanity.com/paper/2507.04350/) (2025)
- [Demarked: A Strategy for Enhanced Abusive Speech Moderation through Counterspeech, Detoxification, and Message Management](https://mlsanity.com/paper/2406.19543/) (2024)
- [Web(er) of Hate: A Survey on How Hate Speech Is Typed](https://mlsanity.com/paper/2506.16190/) (2025)
- [Defining, Understanding, and Detecting Online Toxicity: Challenges and Machine Learning Approaches](https://mlsanity.com/paper/2509.14264/) (2025)

## Abstract (arXiv)

Toxicity has become a grave problem for many online communities and has been growing across many languages, including Russian. Hate speech creates an environment of intimidation, discrimination, and may even incite some real-world violence. Both researchers and social platforms have been focused on developing models to detect toxicity in online communication for a while now. A common problem of these models is the presence of bias towards some words (e.g. woman, black, jew) that are not toxic, but serve as triggers for the classifier due to model caveats. In this paper, we describe our efforts towards classifying hate speech in Russian, and propose simple techniques of reducing unintended bias, such as generating training data with language models using terms and words related to protected identities as context and applying word dropout to such words.