Regional Negative Bias in Word Embeddings Predicts Racial Animus–but only via Name Frequency

by   Austin van Loon, et al.
University of Pennsylvania
Stanford University

The word embedding association test (WEAT) is an important method for measuring linguistic biases against social groups such as ethnic minorities in large text corpora. It does so by comparing the semantic relatedness of words prototypical of the groups (e.g., names unique to those groups) and attribute words (e.g., 'pleasant' and 'unpleasant' words). We show that anti-black WEAT estimates from geo-tagged social media data at the level of metropolitan statistical areas strongly correlate with several measures of racial animus–even when controlling for sociodemographic covariates. However, we also show that every one of these correlations is explained by a third variable: the frequency of Black names in the underlying corpora relative to White names. This occurs because word embeddings tend to group positive (negative) words and frequent (rare) words together in the estimated semantic space. As the frequency of Black names on social media is strongly correlated with Black Americans' prevalence in the population, this results in spurious anti-Black WEAT estimates wherever few Black Americans live. This suggests that research using the WEAT to measure bias should consider term frequency, and also demonstrates the potential consequences of using black-box models like word embeddings to study human cognition and behavior.


page 1

page 2

page 3

page 4


The Dependence on Frequency of Word Embedding Similarity Measures

Recent research has shown that static word embeddings can encode word fr...

Gender Bias in Word Embeddings: A Comprehensive Analysis of Frequency, Syntax, and Semantics

The statistical regularities in language corpora encode well-known socia...

What are the biases in my word embedding?

This paper presents an algorithm for enumerating biases in word embeddin...

Argument from Old Man's View: Assessing Social Bias in Argumentation

Social bias in language - towards genders, ethnicities, ages, and other ...

Frequency-based Distortions in Contextualized Word Embeddings

How does word frequency in pre-training data affect the behavior of simi...

Self-Supervised Euphemism Detection and Identification for Content Moderation

Fringe groups and organizations have a long history of using euphemisms–...

Please sign up or login with your details

Forgot password? Click here to reset