AFRICAN-AMERICAN LANGUAGE USE: IDEOLOGY AND SO-CALLED OBSCENITY

How researchers see this paper

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

The Risk of Racial Bias in Hate Speech Detection (2019, background): “First, and most obviously, the most highly weighted unigrams for predicting “hateful” in FDCL 18 are “n*gga” and “n*ggas”, which are strongly associated with AAE (and their offen-siveness depends on speaker and context; Spears, 1998).”
Challenges in Automated Debiasing for Toxic Language Detection (2021, positive): “Additionally, to ensure less biased toxicity labeling, we recommend recruiting AAE speakers or experts for avoiding over-identification of AAE-markers as toxic (Spears, 1998; Croom, 2013).”
How to do things with slurs: Studies in the way of derogatory words (2013, background): “In fact, slurs are frequently picked up or appropriated by the very ingroup members that the slur was originally intended to target, presumably as a means for like speakers to strengthen in-group solidarity (Kennedy, 2002; Brontsema, 2004; Croom, 2010b, 2011, 2012b; Cameron, 2012a), and scholars hav”
Handling Bias in Toxic Speech Detection: A Survey (2022, methodology): “[120] utilised the few-shot capabilities of the GPT-3 [13] by supplying a few seed examples [92] for Black-oriented to White-oriented dialect conversion.”