Fighting Hate Speech, Silencing Drag Queens? Artificial Intelligence in Content Moderation and Risks to LGBTQ Voices Online

By Thiago Dias Oliva, D. Antonialli, A. Gomes. 2020

156 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Law, Natural Language Processing, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Yejin Choi
2. Noah A. Smith
3. Mohit Bansal
4. Maarten Sap
5. Luke S. Zettlemoyer
6. Percy Liang
7. Swabha Swayamdipta
8. Eric Wallace

In Law

1. Saadia Gabriel
2. Xuhui Zhou
3. Noah A. Smith
4. Yejin Choi
5. Diyi Yang
6. Swabha Swayamdipta
7. Maarten Sap
8. Suchin Gururangan

In Natural Language Processing

1. Yejin Choi
2. Noah A. Smith
3. Maarten Sap
4. Mohit Bansal
5. Swabha Swayamdipta
6. Eric Wallace
7. Diyi Yang
8. Luke S. Zettlemoyer

In Safety, Robustness & Interpretability

1. Maarten Sap
2. Yejin Choi
3. Noah A. Smith
4. Diyi Yang
5. Swabha Swayamdipta
6. Suchin Gururangan
7. Xuhui Zhou
8. Hamid Palangi

Citations in the corpus

• Detoxifying Language Models Risks Marginalizing Minority Voices (2021, methodology): “Similarly, the discrim-inators used by PPLM, GeDi, and Filtering will guide the generated text away from AAE and identity mentions because the discriminators typically consider such text as toxic (Dixon et al., 2018; Sap et al., 2019; Oliva et al., 2020).”
• ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection (2022, background): “Impor-tantly, such biases in toxicity detection risk further marginalizing or censoring minority groups (Yasin, 2018; Sap et al., 2019; Dias Oliva et al., 2020; Are, 2020; Díaz and Hecht-Felella, 2021).”
• Challenges in Automated Debiasing for Toxic Language Detection (2021, background): “Current hate speech or toxic language detection 1 systems exhibit problematic and discriminatory behavior that causes them to have disparate negative impact on minority populations (Yasin, 2018; Guynn, 2020; Kim et al., 2020; Dias Oliva et al., 2020).”
• Sociotechnical Harms: Scoping a Taxonomy for Harm Reduction (2022, background): “Similarly, for content creators, desire to maintain visibility or prevent shadow banning, may lead to increased conforming of content [191].”
• Explaining Toxic Text via Knowledge Enhanced Text Generation (2022, background): “, 2017), as well as cultural differences (Oliva et al., 2020) and racial biases (Xia et al.”
• Sociotechnical Harms of Algorithmic Systems: Scoping a Taxonomy for Harm Reduction (2022, background): “Similarly, patterns of demeaning imagery have been found in hateful natural language predictions about Muslim people [1], and toxicity and sentiment classifiers that are more likely to classify descriptions or mentions of disabilities [113, 213] and LGBTQ identities [215, 237] as toxic or negative.”