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：本文从两大关键视角审视社交网络内容审核：自动化方法（机器审核员）与人工评估者（人工审核员）。我们以前所未有的规模开展噪声审计，使用九个基于知名冒犯性言论数据集训练的机器审核员，对采样自9200万条涉及美国政治多元议题的YouTube评论语料库进行评估。我们首创性地构建了替代性冒犯数据集，向标注员提出两个问题：(1) 他们是否认为某条社交媒体帖子具有冒犯性；(2) 持不同政治立场的标注员会如何看待同一内容的冒犯程度。机器审核员实验表明，不同审核模型的判定结果差异显著。人工审核员实验则揭示：(1) 政治倾向显著影响第一人称冒犯感知视角；(2) 共和党人对替代性冒犯的预测准确率最低；(3) 相比独立派与民主党，预测共和党人的替代性冒犯最具挑战性；(4) 当涉及生育权、枪支管控等敏感议题时，不同政治身份群体的分歧显著加剧。两项实验共同表明，冒犯性确实具有高度主观性，并引发关于内容审核实践的重要思考。