Wide range screening of algorithmic bias in word embedding models using large sentiment lexicons reveals underreported bias types

TL;DR

This study conducts a large-scale analysis of sentiment biases in word embeddings across various social dimensions, revealing underreported bias types and highlighting the complexity and heterogeneity of algorithmic bias.

Contribution

It introduces a comprehensive screening method using large sentiment lexicons to identify diverse and underreported biases in popular word embedding models.

Findings

Systemic bias against African-American names in most models

Gender bias in embeddings is multifaceted and sometimes reversed

Novel biases against socioeconomic status, age, appearance, religion, and politics

Abstract

This work describes a large-scale analysis of sentiment associations in popular word embedding models along the lines of gender and ethnicity but also along the less frequently studied dimensions of socioeconomic status, age, sexual orientation, religious sentiment and political leanings. Consistent with previous scholarly literature, this work has found systemic bias against given names popular among African-Americans in most embedding models examined. Gender bias in embedding models however appears to be multifaceted and often reversed in polarity to what has been regularly reported. Interestingly, using the common operationalization of the term bias in the fairness literature, novel types of so far unreported bias types in word embedding models have also been identified. Specifically, the popular embedding models analyzed here display negative biases against middle and working-class socioeconomic status, male children, senior citizens, plain physical appearance, Islamic religious faith, non-religiosity and conservative political orientation. Reasons for the paradoxical underreporting of these bias types in the relevant literature are probably manifold but widely held blind spots when searching for algorithmic bias and a lack of widespread technical jargon to unambiguously describe a variety of algorithmic associations could conceivably be playing a role. The causal origins for the multiplicity of loaded associations attached to distinct demographic groups within embedding models are often unclear but the heterogeneity of said associations and their potential multifactorial roots raises doubts about the validity of grouping them all under the umbrella term bias. Richer and more fine-grained terminology as well as a more comprehensive exploration of the bias landscape could help the fairness epistemic community to characterize and neutralize algorithmic discrimination more efficiently.