# A Comprehensive View of the Biases of Toxicity and Sentiment Analysis Methods Towards Utterances with African American English Expressions

arXiv: https://arxiv.org/abs/2401.12720 · HTML: https://mlsanity.com/paper/2401.12720/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 67 references that are in the map.
- First posted on arXiv 23 Jan 2024.

## Builds on (most cited first, 14 of 14)

- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them](https://mlsanity.com/paper/1903.03862/) (2019)
- [Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems](https://mlsanity.com/paper/1805.04508/) (2018)
- [Demographic Dialectal Variation in Social Media: A Case Study of African-American English](https://mlsanity.com/paper/1608.08868/) (2016)
- [Deceiving Google's Perspective API Built for Detecting Toxic Comments](https://mlsanity.com/paper/1702.08138/) (2017)
- [A Survey of Race, Racism, and Anti-Racism in NLP](https://mlsanity.com/paper/2106.11410/) (2021)
- [Designing Toxic Content Classification for a Diversity of Perspectives](https://mlsanity.com/paper/2106.04511/) (2021)
- [Fairness Testing: A Comprehensive Survey and Analysis of Trends](https://mlsanity.com/paper/2207.10223/) (2022)
- [All You Need is "Love": Evading Hate-speech Detection](https://mlsanity.com/paper/1808.09115/) (2018)
- [Identification of Bias Against People with Disabilities in Sentiment Analysis and Toxicity Detection Models](https://mlsanity.com/paper/2111.13259/) (2021)
- [Gender Asymmetries in Reality and Fiction: The Bechdel Test of Social Media](https://mlsanity.com/paper/1404.0163/) (2014)

## Built on by (most cited first, 4 of 4)

- [Bring Your Own Prompts: Use-Case-Specific Bias and Fairness Evaluation for LLMs](https://mlsanity.com/paper/2407.10853/) (2024)
- [EnDive: A Cross-Dialect Benchmark for Fairness and Performance in Large Language Models](https://mlsanity.com/paper/2504.07100/) (2025)
- [On the Role of Speech Data in Reducing Toxicity Detection Bias](https://mlsanity.com/paper/2411.08135/) (2024)
- [Disentangling Dialect from Social Bias via Multitask Learning to Improve Fairness](https://mlsanity.com/paper/2406.09977/) (2024)

## Abstract (arXiv)

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.