Vicarious Offense and Noise Audit of Offensive Speech Classifiers : Unifying Human and Machine Disagreement on What is Offensive

Weerasooriya, Tharindu and Dutta, Sujan and Ranasinghe, Tharindu and Zampieri, Marcos and Homan, Christopher and KhudaBukhsh, Ashiqur (2023) Vicarious Offense and Noise Audit of Offensive Speech Classifiers : Unifying Human and Machine Disagreement on What is Offensive. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing :. Association for Computational Linguistics, SGP, pp. 11648-11668. ISBN 9798891760608

Abstract

Offensive speech detection is a key component of content moderation. However, what is offensive can be highly subjective. This paper investigates how machine and human moderators disagree on what is offensive when it comes to real-world social web political discourse. We show that (1) there is extensive disagreement among the moderators (humans and machines); and (2) human and large-language-model classifiers are unable to predict how other human raters will respond, based on their political leanings. For (1), we conduct a ***noise audit*** at an unprecedented scale that combines both machine and human responses. For (2), we introduce a first-of-its-kind dataset of ***vicarious offense***. Our noise audit reveals that moderation outcomes vary wildly across different machine moderators. Our experiments with human moderators suggest that political leanings combined with sensitive issues affect both first-person and vicarious offense. The dataset is available through https://github.com/Homan-Lab/voiced.