This paper examines social web content moderation from two key perspectives: automated methods (machine moderators) and human evaluators (human moderators). We conduct a noise audit at an unprecedented scale using nine machine moderators trained on well-known offensive speech data sets evaluated on a corpus sampled from 92 million YouTube comments discussing a multitude of issues relevant to US politics. We introduce a first-of-its-kind data set of vicarious offense. We ask annotators: (1) if they find a given social media post offensive; and (2) how offensive annotators sharing different political beliefs would find the same content. Our experiments with machine moderators reveal that moderation outcomes wildly vary across different machine moderators. Our experiments with human moderators suggest that (1) political leanings considerably affect first-person offense perspective; (2) Republicans are the worst predictors of vicarious offense; (3) predicting vicarious offense for the Republicans is most challenging than predicting vicarious offense for the Independents and the Democrats; and (4) disagreement across political identity groups considerably increases when sensitive issues such as reproductive rights or gun control/rights are discussed. Both experiments suggest that offense, is indeed, highly subjective and raise important questions concerning content moderation practices.

翻译：本文从两个关键视角审视社交网络内容审核：自动化方法（机器审核员）与人类评估者（人类审核员）。我们基于九种在知名攻击性言论数据集上训练的机器审核员，对来自9200万条YouTube评论（涉及美国政治相关多元议题）的语料库进行评估，以前所未有的规模开展噪声审计。我们首次引入"越轨冒犯"数据集，要求标注者回答：（1）是否认为特定社交媒体帖子具有冒犯性；（2）持不同政治立场的标注者会如何评价相同内容的冒犯程度。机器审核员实验表明，不同审核模型对内容审核结果存在显著差异。人类审核员实验揭示：（1）政治倾向显著影响第一人称冒犯感知；（2）共和党人对越轨冒犯的预测准确性最差；（3）相比独立派与民主党，预测共和党人的越轨冒犯最具挑战性；（4）涉及生殖权利或枪支管控/权利等敏感议题时，不同政治身份群体间的分歧显著加剧。两项实验共同表明，冒犯性确具高度主观性，并对内容审核实践提出重要反思。