paper-with-me

홈 › Papers

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

2023-01-29 · Tharindu Cyril Weerasooriya, Sujan Dutta, Tharindu Ranasinghe, Marcos Zampieri, Christopher M. Homan, Ashiqur R. KhudaBukhsh

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.

📄 PDF Abstract BibTeX arXiv:2301.12534

Code (2)

homan-lab/noise-audit-dataset 공식 구현
homan-lab/voiced 공식 구현

Tasks

Language ModelingLanguage ModellingLarge Language ModelMachine Translation

Similar Papers 제목 키워드 기반

DeepAnalyzer at SemEval-2019 Task 6: A deep learning-based ensemble method for identifying offensive tweets

2019-06-01 · SEMEVAL 2019 6 · Gretel Liz De la Pe{\~n}a, Paolo Rosso

This paper describes the system we developed for SemEval 2019 on Identifying and Categorizing Offensive Language in Social Media (OffensEval - Task 6). The task focuses on offensive language in tweets. It is organized in…

Language IdentificationPart-Of-Speech Tagging

Rater Cohesion and Quality from a Vicarious Perspective

2024-08-15 · Deepak Pandita, Tharindu Cyril Weerasooriya, Sujan Dutta, Sarah K. Luger 외

Human feedback is essential for building human-centered AI systems across domains where disagreement is prevalent, such as AI safety, content moderation, or sentiment analysis. Many disagreements, particularly in politic…

Sentiment Analysis

Amobee at SemEval-2019 Tasks 5 and 6: Multiple Choice CNN Over Contextual Embedding

2019-04-17 · SEMEVAL 2019 6 · Alon Rozental, Dadi Biton

This article describes Amobee's participation in "HatEval: Multilingual detection of hate speech against immigrants and women in Twitter" (task 5) and "OffensEval: Identifying and Categorizing Offensive Language in Socia…

Multiple-choice

IR3218-UI at SemEval-2020 Task 12: Emoji Effects on Offensive Language IdentifiCation

2020-12-01 · SEMEVAL 2020 · Sandy Kurniawan, Indra Budi, Muhammad Okky Ibrohim

In this paper, we present our approach and the results of our participation in OffensEval 2020. There are three sub-tasks in OffensEval 2020 namely offensive language identification (sub-task A), automatic categorization…

Language Identification

Detecting Abusive Albanian

2021-07-28 · Erida Nurce, Jorgel Keci, Leon Derczynski

The ever growing usage of social media in the recent years has had a direct impact on the increased presence of hate speech and offensive speech in online platforms. Research on effective detection of such content has ma…

Hate Speech Detection