Detecting East Asian Prejudice on Social Media
Detecting East Asian Prejudice on Social Media
复制标题
检测社交媒体上的东亚偏见
DOI：
10.18653/v1/2020.alw-1.19
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Scott A. Hale
中科院分区：
文献类型：
--
作者：
Bertie Vidgen;Austin Botelho;David A. Broniatowski;E. Guest;Matthew Hall;H. Margetts;Rebekah Tromble;Zeerak Talat;Scott A. Hale
在COVID-19期间，人们对网上传播攻击性和仇恨性语言的担忧加剧，特别是针对东亚和东亚人民的敌意。我们报告了一个新的数据集和一个机器学习分类器的创建，该分类器将Twitter上的社交媒体帖子分为四类：对东亚的敌意，对东亚的批评，对东亚偏见的元讨论和中立类。该分类器实现了0.83的宏F1分数。然后，我们进行了深入的错误分析，并表明该模型与边缘情况和模糊内容作斗争。我们提供了20，000个tweet训练数据集（由经验丰富的分析师注释），其中还包含几个二级类别和其他标志。我们还提供了40，000个原始注释（裁定前），完整的代码本，COVID-19相关性和东亚相关性的注释以及1，000个标签的立场，以及最终模型。
During COVID-19 concerns have heightened about the spread of aggressive and hateful language online, especially hostility directed against East Asia and East Asian people. We report on a new dataset and the creation of a machine learning classifier that categorizes social media posts from Twitter into four classes: Hostility against East Asia, Criticism of East Asia, Meta-discussions of East Asian prejudice, and a neutral class. The classifier achieves a macro-F1 score of 0.83. We then conduct an in-depth ground-up error analysis and show that the model struggles with edge cases and ambiguous content. We provide the 20,000 tweet training dataset (annotated by experienced analysts), which also contains several secondary categories and additional flags. We also provide the 40,000 original annotations (before adjudication), the full codebook, annotations for COVID-19 relevance and East Asian relevance and stance for 1,000 hashtags, and the final model.