Race, Perceptions of Femininity, and the Power of the First Lady: A Comparative Analysis

By Andra Gillespie. 2016

How researchers see this paper

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

CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models (2020, background): “If their example could satisfy multiple bias types, like the angry black woman stereotype (Collins, 2005; Madison, 2009; Gillespie, 2016), they are asked to 1https://www.eeoc.gov/ prohibited-employment-policiespractices tag the example with the single bias type they think fits best.”
On Measuring Social Biases in Sentence Encoders (2019, methodology): “…on bias in NLP, we also introduce tests of two biases that are less amenable to word-level representation: the angry black woman stereotype (Collins, 2004; Madison, 2009; Harris-Perry, 2011; hooks, 2015; Gillespie, 2016) and a double bind on women in professional settings (Heilman et al., 2004).”