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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Weerasooriya, Tharindu Cyril, Dutta, Sujan, Ranasinghe, Tharindu, Zampieri, Marcos, Homan, Christopher M., KhudaBukhsh, Ashiqur R.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915771832074240
author Weerasooriya, Tharindu Cyril
Dutta, Sujan
Ranasinghe, Tharindu
Zampieri, Marcos
Homan, Christopher M.
KhudaBukhsh, Ashiqur R.
author_facet Weerasooriya, Tharindu Cyril
Dutta, Sujan
Ranasinghe, Tharindu
Zampieri, Marcos
Homan, Christopher M.
KhudaBukhsh, Ashiqur R.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2301_12534
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Vicarious Offense and Noise Audit of Offensive Speech Classifiers: Unifying Human and Machine Disagreement on What is Offensive
Weerasooriya, Tharindu Cyril
Dutta, Sujan
Ranasinghe, Tharindu
Zampieri, Marcos
Homan, Christopher M.
KhudaBukhsh, Ashiqur R.
Computation and Language
Computers and Society
Machine Learning
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.
title Vicarious Offense and Noise Audit of Offensive Speech Classifiers: Unifying Human and Machine Disagreement on What is Offensive
topic Computation and Language
Computers and Society
Machine Learning
url https://arxiv.org/abs/2301.12534