# Comparative Studies of Detecting Abusive Language on Twitter

arXiv: https://arxiv.org/abs/1808.10245 · HTML: https://mlsanity.com/paper/1808.10245/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Aug 2018.

## Built on by (most cited first, 9 of 9)

- [Towards generalisable hate speech detection: a review on obstacles and solutions](https://mlsanity.com/paper/2102.08886/) (2021)
- [Abuse is Contextual, What about NLP? The Role of Context in Abusive Language Annotation and Detection](https://mlsanity.com/paper/2103.14916/) (2021)
- [Hopeful_Men@LT-EDI-EACL2021: Hope Speech Detection Using Indic Transliteration and Transformers](https://mlsanity.com/paper/2102.12082/) (2021)
- [MIPT-NSU-UTMN at SemEval-2021 Task 5: Ensembling Learning with Pre-trained Language Models for Toxic Spans Detection](https://mlsanity.com/paper/2104.04739/) (2021)
- [LaDiff ULMFiT: A Layer Differentiated training approach for ULMFiT](https://mlsanity.com/paper/2101.04965/) (2021)
- [Improving Automatic Hate Speech Detection with Multiword Expression Features](https://mlsanity.com/paper/2106.00237/) (2021)
- [How Do Pedophiles Tweet? Investigating the Writing Styles and Online Personas of Child Cybersex Traffickers in the Philippines](https://mlsanity.com/paper/2107.09881/) (2021)
- [Transferring Knowledge via Neighborhood-Aware Optimal Transport for Low-Resource Hate Speech Detection](https://mlsanity.com/paper/2210.09340/) (2022)
- [Textual Toxicity in Social Media: Understanding the Bangla Toxic Language Expressed in Facebook Comment](https://mlsanity.com/paper/2312.05467/) (2023)

## Abstract (arXiv)

The context-dependent nature of online aggression makes annotating large collections of data extremely difficult. Previously studied datasets in abusive language detection have been insufficient in size to efficiently train deep learning models. Recently, Hate and Abusive Speech on Twitter, a dataset much greater in size and reliability, has been released. However, this dataset has not been comprehensively studied to its potential. In this paper, we conduct the first comparative study of various learning models on Hate and Abusive Speech on Twitter, and discuss the possibility of using additional features and context data for improvements. Experimental results show that bidirectional GRU networks trained on word-level features, with Latent Topic Clustering modules, is the most accurate model scoring 0.805 F1.