Handling Disagreement in Hate Speech Modelling

Petra Kralj Novak, Teresa Scantamburlo, Andraž Pelicon, Matteo Cinelli, Igor Mozetič, Fabiana Zollo*

*Corresponding author for this work

Research output: Contribution to Book/Report typesConference contributionpeer-review

Abstract (may include machine translation)

Hate speech annotation for training machine learning models is an inherently ambiguous and subjective task. In this paper, we adopt a perspectivist approach to data annotation, model training and evaluation for hate speech classification. We first focus on the annotation process and argue that it drastically influences the final data quality. We then present three large hate speech datasets that incorporate annotator disagreement and use them to train and evaluate machine learning models. As the main point, we propose to evaluate machine learning models through the lens of disagreement by applying proper performance measures to evaluate both annotators’ agreement and models’ quality. We further argue that annotator agreement poses intrinsic limits to the performance achievable by models. When comparing models and annotators, we observed that they achieve consistent levels of agreement across datasets. We reflect upon our results and propose some methodological and ethical considerations that can stimulate the ongoing discussion on hate speech modelling and classification with disagreement.

Original languageEnglish
Title of host publicationInformation Processing and Management of Uncertainty in Knowledge-Based Systems - 19th International Conference, IPMU 2022, Proceedings
EditorsDavide Ciucci, Inés Couso, Jesús Medina, Dominik Ślęzak, Davide Petturiti, Bernadette Bouchon-Meunier, Ronald R. Yager
PublisherSpringer Science and Business Media Deutschland GmbH
Pages681-695
Number of pages15
ISBN (Print)9783031089732
DOIs
StatePublished - 2022
Event19th International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems, IPMU 2022 - Milan, Italy
Duration: 11 Jul 202215 Jul 2022

Publication series

NameCommunications in Computer and Information Science
Volume1602 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference19th International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems, IPMU 2022
Country/TerritoryItaly
CityMilan
Period11/07/2215/07/22

Keywords

  • Annotator agreement
  • Diamond standard evaluation
  • Hate speech

Fingerprint

Dive into the research topics of 'Handling Disagreement in Hate Speech Modelling'. Together they form a unique fingerprint.

Cite this