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

By David Rozado. 2020

52 citations recorded by the source corpus.

Concerns about gender bias in word embedding models have captured substantial attention in the algorithmic bias research literature. Other bias types however have received lesser amounts of scrutiny. 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, physical appearance, 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 and intellectual phenomena such as 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.

Subfields: Artificial Intelligence, General Social Sciences, Sociology and Political Science, Representation & Self-Supervised Learning, 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

In General Social Sciences

In Sociology and Political Science

In Representation & Self-Supervised Learning

In Safety, Robustness & Interpretability

Citations in the corpus

Language (Technology) is Power: A Critical Survey of “Bias” in NLP (2020, background): “lyzing “bias” in NLP systems often state multiple motivations (e.g., Hovy and Spruit, 2016; Bender, 2019; Sun et al., 2019; Rozado, 2020; Shah et al., 2020).”
CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models (2020, background): “Rozado (2020) extend Caliskan et al.’s findings and show that popular pretrained word embeddings also display biases based on age, religion, and socioeconomic status.”
The Political Biases of ChatGPT (2023, background): “The topic of political bias in AI systems has received a comparatively limited amount of attention in comparison to other algorithmic bias types (Rozado 2020).”