# Predictive Embeddings for Hate Speech Detection on Twitter

arXiv: https://arxiv.org/abs/1809.10644 · HTML: https://mlsanity.com/paper/1809.10644/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Sep 2018.

## Built on by (most cited first, 12 of 12)

- [Abuse is Contextual, What about NLP? The Role of Context in Abusive Language Annotation and Detection](https://mlsanity.com/paper/2103.14916/) (2021)
- [ToxiCraft: A Novel Framework for Synthetic Generation of Harmful Information](https://mlsanity.com/paper/2409.14740/) (2024)
- [Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvements](https://mlsanity.com/paper/2302.09270/) (2023)
- [Multi-modal Hate Speech Detection using Machine Learning](https://mlsanity.com/paper/2307.11519/) (2023)
- [Why Is It Hate Speech? Masked Rationale Prediction for Explainable Hate Speech Detection](https://mlsanity.com/paper/2211.00243/) (2022)
- [Sexism detection: The first corpus in Algerian dialect with a code-switching in Arabic/ French and English](https://mlsanity.com/paper/2104.01443/) (2021)
- [CRUSH: Contextually Regularized and User anchored Self-supervised Hate speech Detection](https://mlsanity.com/paper/2204.06389/) (2022)
- [ToxiLab: How Well Do Open-Source LLMs Generate Synthetic Toxicity Data?](https://mlsanity.com/paper/2411.15175/) (2024)
- [Dynamic Content Moderation in Livestreams: Combining Supervised Classification with MLLM-Boosted Similarity Matching](https://mlsanity.com/paper/2512.03553/) (2025)
- [Multi-Task Text Classification using Graph Convolutional Networks for Large-Scale Low Resource Language](https://mlsanity.com/paper/2205.01204/) (2022)
- [dictNN: A Dictionary-Enhanced CNN Approach for Classifying Hate Speech on Twitter](https://mlsanity.com/paper/2103.08780/) (2021)
- [Cross-Platform and Cross-Domain Abusive Language Detection with Supervised Contrastive Learning](https://mlsanity.com/paper/2211.06452/) (2022)

## Abstract (arXiv)

We present a neural-network based approach to classifying online hate speech in general, as well as racist and sexist speech in particular. Using pre-trained word embeddings and max/mean pooling from simple, fully-connected transformations of these embeddings, we are able to predict the occurrence of hate speech on three commonly used publicly available datasets. Our models match or outperform state of the art F1 performance on all three datasets using significantly fewer parameters and minimal feature preprocessing compared to previous methods.