Automated Hate Speech Detection and the Problem of Offensive Language

By Thomas Davidson, Dana Warmsley, Michael W. Macy, Ingmar Weber. 2017

3,212 citations recorded by the source corpus.

A key challenge for automatic hate-speech detection on social media is the separation of hate speech from other instances of offensive language. Lexical detection methods tend to have low precision because they classify all messages containing particular terms as hate speech and previous work using supervised learning has failed to distinguish between the two categories. We used a crowd-sourced hate speech lexicon to collect tweets containing hate speech keywords. We use crowd-sourcing to label a sample of these tweets into three categories: those containing hate speech, only offensive language, and those with neither. We train a multi-class classifier to distinguish between these different categories. Close analysis of the predictions and the errors shows when we can reliably separate hate speech from other offensive language and when this differentiation is more difficult. We find that racist and homophobic tweets are more likely to be classified as hate speech but that sexist tweets are generally classified as offensive. Tweets without explicit hate keywords are also more difficult to classify.

Subfields: Artificial Intelligence, Information Systems, Natural Language Processing, Safety, Robustness & Interpretability, AI Ethics, Fairness & Society

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Mohit Bansal
  2. Yejin Choi
  3. Noah A. Smith
  4. Jason Aaron Edward Weston
  5. Percy Liang
  6. Jianfeng Gao
  7. Luke S. Zettlemoyer
  8. Graham Neubig

In Information Systems

  1. Bertie Vidgen
  2. Isar Nejadgholi
  3. Svetlana Kiritchenko
  4. Jason Aaron Edward Weston
  5. Yejin Choi
  6. Leon Derczynski
  7. Xiang Ren
  8. Ziqi Zhang

In Natural Language Processing

  1. Yejin Choi
  2. Mohit Bansal
  3. Jason Aaron Edward Weston
  4. Noah A. Smith
  5. Yulia Tsvetkov
  6. Douwe Kiela
  7. Emily Dinan
  8. Graham Neubig

In Safety, Robustness & Interpretability

  1. Isar Nejadgholi
  2. Svetlana Kiritchenko
  3. Yulia Tsvetkov
  4. Bertie Vidgen
  5. Yejin Choi
  6. Noah A. Smith
  7. Valerio Basile
  8. Maarten Sap

In AI Ethics, Fairness & Society

  1. Bertie Vidgen
  2. Valerio Basile
  3. Leon Derczynski
  4. Marcos Zampieri
  5. Isar Nejadgholi
  6. Viviana Patti
  7. Björn Gambäck
  8. Mladen Karan

Citations in the corpus