# Neural Character-based Composition Models for Abuse Detection

arXiv: https://arxiv.org/abs/1809.00378 · HTML: https://mlsanity.com/paper/1809.00378/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Sep 2018.

## Built on by (most cited first, 11 of 11)

- [Towards generalisable hate speech detection: a review on obstacles and solutions](https://mlsanity.com/paper/2102.08886/) (2021)
- [Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvements](https://mlsanity.com/paper/2302.09270/) (2023)
- [Towards Equal Gender Representation in the Annotations of Toxic Language Detection](https://mlsanity.com/paper/2106.02183/) (2021)
- [Automated Identification of Toxic Code Reviews Using ToxiCR](https://mlsanity.com/paper/2202.13056/) (2022)
- [Leveraging cross-platform data to improve automated hate speech detection](https://mlsanity.com/paper/2102.04895/) (2021)
- [Analysis of Twitter Users' Lifestyle Choices using Joint Embedding Model](https://mlsanity.com/paper/2104.03189/) (2021)
- [Twitter User Representation Using Weakly Supervised Graph Embedding](https://mlsanity.com/paper/2108.08988/) (2021)
- [The State of Profanity Obfuscation in Natural Language Processing](https://mlsanity.com/paper/2210.07595/) (2022)
- [A Taxonomy of Rater Disagreements: Surveying Challenges & Opportunities from the Perspective of Annotating Online Toxicity](https://mlsanity.com/paper/2311.04345/) (2023)
- [Cross-Platform and Cross-Domain Abusive Language Detection with Supervised Contrastive Learning](https://mlsanity.com/paper/2211.06452/) (2022)
- [Improved two-stage hate speech classification for twitter based on Deep Neural Networks](https://mlsanity.com/paper/2206.04162/) (2022)

## Abstract (arXiv)

The advent of social media in recent years has fed into some highly undesirable phenomena such as proliferation of offensive language, hate speech, sexist remarks, etc. on the Internet. In light of this, there have been several efforts to automate the detection and moderation of such abusive content. However, deliberate obfuscation of words by users to evade detection poses a serious challenge to the effectiveness of these efforts. The current state of the art approaches to abusive language detection, based on recurrent neural networks, do not explicitly address this problem and resort to a generic OOV (out of vocabulary) embedding for unseen words. However, in using a single embedding for all unseen words we lose the ability to distinguish between obfuscated and non-obfuscated or rare words. In this paper, we address this problem by designing a model that can compose embeddings for unseen words. We experimentally demonstrate that our approach significantly advances the current state of the art in abuse detection on datasets from two different domains, namely Twitter and Wikipedia talk page.