# Seeing Hate Differently: Hate Subspace Modeling for Culture-Aware Hate Speech Detection

arXiv: https://arxiv.org/abs/2510.13837 · HTML: https://mlsanity.com/paper/2510.13837/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 13 references that are in the map.
- First posted on arXiv 11 Oct 2025.

## Builds on (most cited first, 8 of 8)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification](https://mlsanity.com/paper/2010.12421/) (2020)
- [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://mlsanity.com/paper/1911.03891/) (2019)
- [BERTweet: A pre-trained language model for English Tweets](https://mlsanity.com/paper/2005.10200/) (2020)
- [HateBERT: Retraining BERT for Abusive Language Detection in English](https://mlsanity.com/paper/2010.12472/) (2020)
- [TwHIN-BERT: A Socially-Enriched Pre-trained Language Model for Multilingual Tweet Representations at Twitter](https://mlsanity.com/paper/2209.07562/) (2022)
- [Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysis](https://mlsanity.com/paper/2308.16705/) (2023)

## Abstract (arXiv)

Hate speech detection has been extensively studied, yet existing methods often overlook a real-world complexity: training labels are biased, and interpretations of what is considered hate vary across individuals with different cultural backgrounds. We first analyze these challenges, including data sparsity, cultural entanglement, and ambiguous labeling. To address them, we propose a culture-aware framework that constructs individuals' hate subspaces. To alleviate data sparsity, we model combinations of cultural attributes. For cultural entanglement and ambiguous labels, we use label propagation to capture distinctive features of each combination. Finally, individual hate subspaces, which in turn can further enhance classification performance. Experiments show our method outperforms state-of-the-art by 1.05% on average across all metrics.