Language is a dynamic aspect of our culture that changes when expressed in different technologies/communities. Online social networks have enabled the diffusion and evolution of different dialects, including African American English (AAE). However, this increased usage is not without barriers. One particular barrier is how sentiment (Vader, TextBlob, and Flair) and toxicity (Google's Perspective and the open-source Detoxify) methods present biases towards utterances with AAE expressions. Consider Google's Perspective to understand bias. Here, an utterance such as ``All n*ggers deserve to die respectfully. The police murder us.'' it reaches a higher toxicity than ``African-Americans deserve to die respectfully. The police murder us.''. This score difference likely arises because the tool cannot understand the re-appropriation of the term ``n*gger''. One explanation for this bias is that AI models are trained on limited datasets, and using such a term in training data is more likely to appear in a toxic utterance. While this may be plausible, the tool will make mistakes regardless. Here, we study bias on two Web-based (YouTube and Twitter) datasets and two spoken English datasets. Our analysis shows how most models present biases towards AAE in most settings. We isolate the impact of AAE expression usage via linguistic control features from the Linguistic Inquiry and Word Count (LIWC) software, grammatical control features extracted via Part-of-Speech (PoS) tagging from Natural Language Processing (NLP) models, and the semantic of utterances by comparing sentence embeddings from recent language models. We present consistent results on how a heavy usage of AAE expressions may cause the speaker to be considered substantially more toxic, even when speaking about nearly the same subject. Our study complements similar analyses focusing on small datasets and/or one method only.

翻译：[translated abstract in Chinese] 语言是我们文化中的一个动态方面，它会随着在不同技术/社区中的表达而变化。在线社交网络促进了包括非裔美国人英语（AAE）在内的不同方言的传播与演变。然而，这种使用的增加并非没有障碍。一个具体障碍在于情感分析（Vader、TextBlob和Flair）与毒性检测方法（Google的Perspective和开源工具Detoxify）对含有AAE表达的话语存在偏差。以Google的Perspective为例理解这种偏差：诸如“All n*ggers deserve to die respectfully. The police murder us.”的表述，其毒性得分高于“African-Americans deserve to die respectfully. The police murder us.”。这种分数差异很可能源于工具无法理解“n*gger”一词的重新挪用。对此偏差的一种解释是，AI模型训练于有限的数据库，而该术语在训练数据中更可能出现在毒性话语中。尽管这一解释可能合理，但工具无论如何都会出错。本研究基于两个网络数据集（YouTube和Twitter）和两个英语口语数据集分析偏差。结果显示，大多数模型在多数情境下对AAE表达存在偏差。我们通过Linguistic Inquiry and Word Count（LIWC）软件提取的 linguistic 控制特征、自然语言处理（NLP）模型经词性标注（PoS）提取的语法控制特征，以及通过对比近期语言模型的句子嵌入来研究话语的语义，从而隔离AAE表达使用的影响。我们呈现了一致的结果：即使谈论近乎相同的话题，大量使用AAE表达也可能导致说话者被认为具有显著更高的毒性。本研究补充了仅聚焦于小规模数据集或单一方法的类似分析。