反犹太主义的毒性有多强？针对反犹太主义在线内容的自动化毒性评分的潜力与局限性
How toxic is antisemitism? Potentials and limitations of automated toxicity scoring for antisemitic online content
AI总结：
本研究针对谷歌与Jigsaw推出的Perspective API，利用约3600条德语社交媒体标注数据，评估其检测反犹太主义在线内容的效果，发现其存在非显性反犹内容识别差、易被反犹暗语绕过等局限。
摘要：
Perspective API是由谷歌和Jigsaw推出的一款流行的文本毒性评估服务，已在内容审核、监测和社交媒体研究等多个应用领域得到广泛采用。我们考察了它在检测反犹太主义在线内容方面的潜力与局限性，这类内容从定义上属于毒性的涵盖范畴。我们使用一个包含约3600条来自Telegram和Twitter的帖子的人工标注德语数据集，探究反犹太主义文本被评定的毒性程度，以及毒性评分在反犹太主义的不同子形式和文本所表达的立场方面存在的差异。我们发现，在基础层面上，Perspective API能够识别出反犹太主义内容具有毒性，但在非显性形式的反犹太主义以及对其持批判立场的文本方面存在严重缺陷。此外，通过简单的文本操作，我们证明使用广泛传播的反犹太主义暗语可以大幅降低API的评分，这使得绕过基于该服务结果的内容审核变得相当容易。
英文摘要：
The Perspective API, a popular text toxicity assessment service by Google and Jigsaw, has found wide adoption in several application areas, notably content moderation, monitoring, and social media research. We examine its potentials and limitations for the detection of antisemitic online content that, by definition, falls under the toxicity umbrella term. Using a manually annotated German-language dataset comprising around 3,600 posts from Telegram and Twitter, we explore as how toxic antisemitic texts are rated and how the toxicity scores differ regarding different subforms of antisemitism and the stance expressed in the texts. We show that, on a basic level, Perspective API recognizes antisemitic content as toxic, but shows critical weaknesses with respect to non-explicit forms of antisemitism and texts taking a critical stance towards it. Furthermore, using simple text manipulations, we demonstrate that the use of widespread antisemitic codes can substantially reduce API scores, making it rather easy to bypass content moderation based on the service's results.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
