Racial diversity has become increasingly discussed within the AI and algorithmic fairness literature, yet little attention is focused on justifying the choices of racial categories and understanding how people are racialized into these chosen racial categories. Even less attention is given to how racial categories shift and how the racialization process changes depending on the context of a dataset or model. An unclear understanding of \textit{who} comprises the racial categories chosen and \textit{how} people are racialized into these categories can lead to varying interpretations of these categories. These varying interpretations can lead to harm when the understanding of racial categories and the racialization process is misaligned from the actual racialization process and racial categories used. Harm can also arise if the racialization process and racial categories used are irrelevant or do not exist in the context they are applied. In this paper, we make two contributions. First, we demonstrate how racial categories with unclear assumptions and little justification can lead to varying datasets that poorly represent groups obfuscated or unrepresented by the given racial categor
Deep learning models can identify racial identity with high accuracy from chest X-ray (CXR) recordings. Thus, there is widespread concern about the potential for racial shortcut learning, where a model inadvertently learns to systematically bias its diagnostic predictions as a function of racial identity. Such racial biases threaten healthcare equity and model reliability, as models may systematically misdiagnose certain demographic groups. Since racial shortcuts are diffuse - non-localized and distributed throughout the whole CXR recording - image preprocessing methods may influence racial shortcut learning, yet the potential of such methods for reducing biases remains underexplored. Here, we investigate the effects of image preprocessing methods including lung masking, lung cropping, and Contrast Limited Adaptive Histogram Equalization (CLAHE). These approaches aim to suppress spurious cues encoding racial information while preserving diagnostic accuracy. Our experiments reveal that simple bounding box-based lung cropping can be an effective strategy for reducing racial shortcut learning while maintaining diagnostic model performance, bypassing frequently postulated fairness-accu
Racial homophily refers to the tendency of individuals to associate with others of the same racial or ethnic background. A recent study found no evidence of racial homophily in responses to mass shooting data visualizations. To increase the likelihood of detecting an effect, we redesigned the experiment by replacing bar charts with anthropographics and expanding the sample size. In a crowdsourced study (N=720), we showed participants a pictograph of mass shooting victims in the United States, with victims from one of three racial groups (Hispanic, Black, or White) highlighted. Each participant was assigned a visualization highlighting either their own racial group or a different racial group, allowing us to assess the influence of racial concordance on changes in affect (emotion). We found that, across all conditions, racial concordance had a modest but significant effect on changes in affect, with participants experiencing greater negative affect change when viewing visualizations highlighting their own race. This study provides initial evidence that racial homophily can emerge in responses to data visualizations, particularly when using anthropographics.
Inferring racial discrimination in police use of force -- the average causal effect of civilian race on use of force -- requires two assumptions about policing prior to potential use of force: that officers do not discriminate in whom they would stop (no discrimination in stops) and that, conditional on patrol context, the probability that an encounter is with a minority rather than a white civilian does not vary across encounters (no bias in encounters). As Knox et al. (2020) show, violations of the first can mask racial disparity in force. Whether it reflects discrimination in force also depends on the second. Existing sensitivity analyses address one assumption at a time. We develop a framework that varies both sequentially and apply it to NYPD Stop, Question, and Frisk data (2003--2013). Under plausible levels of discrimination in stops, we find substantial racial disparity in force. However, the conclusion that this disparity reflects discrimination is fragile to modest departures from no bias in encounters that census-based calibration suggests are demographically feasible. By jointly addressing both confounding channels, the framework reveals how they interact in ways that s
Urban segregation research has long relied on residential patterns, yet growing evidence suggests that racial/ethnic segregation also manifests systematically in mobility behaviors. Leveraging anonymized mobile device data from New York City before and during the COVID-19 pandemic, we develop a network-analytic framework to dissect mobility segregation in racialized flow networks. We examine citywide racial mixing patterns through mixing matrices and assortativity indices, revealing persistent diagonal dominance where intra-group flows constituted 69.27% of total movements. Crucially, we develop a novel dual-metric framework that reconceptualizes mobility segregation as two interlocking dimensions: structural segregation-passive exposure patterns driven by residential clustering, and preferential segregation-active homophily in mobility choices beyond spatial constraints. Our gravity-adjusted indices reveal that racial divisions transcend residential clustering-all racial groups exhibit active homophily after spatial adjustments, with particularly severe isolation during the pandemic. Findings highlight how pandemic restrictions disproportionately amplified asymmetric isolation, wi
Racial differences in authoritarianism are widely used to explain variation in political attitudes, yet it is unclear whether they reflect true latent differences or measurement artifacts. Using anchor-based multi-group confirmatory factor analysis across multiple nationally representative surveys, this paper examines measurement equivalence in the standard child-rearing authoritarianism battery. We find systematic differences in how respondents use response categories across groups. Accounting for this non-invariance alters but does not eliminate racial differences in authoritarianism; African Americans continue to exhibit higher latent authoritarianism under partial scalar invariance. However, conventional multi-item scales substantially attenuate the association between authoritarianism and policy attitudes. These results show that measurement non-invariance is not merely a technical concern but can meaningfully shape substantive inferences about racial differences and their political consequences, underscoring the importance of explicit measurement modeling in studies of public opinion and political behavior.
This paper examines whether increased awareness can affect racial bias and colorism. We exploit a natural experiment arising from the widespread publicity of Price and Wolfers (2010), which served as an external shock, intensifying scrutiny of racial bias in men's basketball officiating. We investigate refereeing decisions in a similar setting, the Women's National Basketball Association (WNBA), which is known as a progressive institution with a longstanding commitment to diversity, equity, and inclusion (DEI) policy. We apply state-of-the-art artificial intelligence and machine learning techniques to systematically predict race and objectively measure skin tone. Our empirical strategy exploits the quasi-random assignment of referees to games, combined with high-dimensional fixed effects, to estimate the relationship between the racial and skin tone compositions of referees and players, as well as foul-calling behavior. Our results show no significant racial bias before the intense media coverage. However, afterward, we find evidence of overcorrection: a player earns fewer fouls when facing more referees from the opposite race and skin tone. Even though this overcorrection seems to
Racial disparities in recidivism remain a persistent challenge within the criminal justice system, increasingly exacerbated by the adoption of algorithmic risk assessment tools. Past works have primarily focused on bias induced by these tools, treating recidivism as a binary outcome. Limited attention has been given to non-algorithmic factors (including socioeconomic ones) in driving racial disparities from a systemic perspective. To that end, this work presents a multi-stage causal framework to investigate the advent and extent of disparities by considering time-to-recidivism rather than a simple binary outcome. The framework captures interactions among races, the algorithm, and contextual factors. This work introduces the notion of counterfactual racial disparity and offers a formal test using survival analysis that can be conducted with observational data to assess if differences in recidivism arise from algorithmic bias, contextual factors, or their interplay. In particular, it is formally established that if sufficient statistical evidence for differences across racial groups is observed, it would support rejecting the null hypothesis that non-algorithmic factors (including so
Although there is widespread recognition of racial bias in US law, it is unclear how such bias appears in the language of law, namely judicial opinions, and whether it varies across time period or region. Building upon approaches for measuring implicit racial bias in large-scale corpora, we approximate GloVe word embeddings for over 6 million US federal and state court cases from 1860 to 2009. We find strong evidence of racial bias across nearly all regions and time periods, as traditionally Black names are more closely associated with pre-classified "unpleasant" terms whereas traditionally White names are more closely associated with pre-classified "pleasant" terms. We also test whether legal opinions before 1950 exhibit more implicit racial bias than those after 1950, as well as whether opinions from Southern states exhibit less change in racial bias than those from Northeastern states. We do not find evidence of elevated bias in legal opinions before 1950, or evidence that legal opinions from Northeastern states show greater change in racial bias over time compared to Southern states. These results motivate further research into institutionalized racial bias.
Generative adversarial networks (GANs) have demonstrated significant progress in unpaired image-to-image translation in recent years for several applications. CycleGAN was the first to lead the way, although it was restricted to a pair of domains. StarGAN overcame this constraint by tackling image-to-image translation across various domains, although it was not able to map in-depth low-level style changes for these domains. Style mapping via reference-guided image synthesis has been made possible by the innovations of StarGANv2 and StyleGAN. However, these models do not maintain individuality and need an extra reference image in addition to the input. Our study aims to translate racial traits by means of multi-domain image-to-image translation. We present RaceGAN, a novel framework capable of mapping style codes over several domains during racial attribute translation while maintaining individuality and high level semantics without relying on a reference image. RaceGAN outperforms other models in translating racial features (i.e., Asian, White, and Black) when tested on Chicago Face Dataset. We also give quantitative findings utilizing InceptionReNetv2-based classification to demon
Legal reform can be challenging in light of the volume, complexity, and interdependence of laws, codes, and records. One salient example of this challenge is the effort to restrict and remove racially restrictive covenants, clauses in property deeds that historically barred individuals of specific races from purchasing homes. Despite the Supreme Court holding such racial covenants unenforceable in 1948, they persist in property records across the United States. Many jurisdictions have moved to identify and strike these provisions, including California, which mandated in 2021 that all counties implement such a process. Yet the scale can be overwhelming, with Santa Clara County (SCC) alone having over 24 million property deed documents, making purely manual review infeasible. We present a novel approach to addressing this pressing issue, developed through a partnership with the SCC Clerk-Recorder's Office. First, we leverage an open large language model, finetuned to detect racial covenants with high precision and recall. We estimate that this system reduces manual efforts by 86,500 person hours and costs less than 2% of the cost for a comparable off-the-shelf closed model. Second, w
Autocomplete is a popular search feature that predicts queries based on user input and guides users to a set of potentially relevant suggestions. In this study, we examine what YouTube autocompletes suggest to users seeking information about race on the platform. Specifically, we perform an algorithm output audit of autocomplete suggestions for input queries about four racial groups and examine the stereotypes they embody. Using critical discourse analysis, we identify five major sociocultural contexts in which racial information appears -Appearance, Ability, Culture, Social Equity, and Manner. We found that the participatory nature of YouTube produces a multifaceted representation of race-related content in its search outputs, characterized by enduring historical biases, aggregated discrimination, and interracial tensions, while simultaneously depicting minority resistance and aspirations of a post-racial society. We call for innovations in content moderation policy design and enforcement to address existing racial harms in YouTube search outputs.
Racial disproportionality in stop and search practices elicits substantial concerns about its societal and behavioral impacts. In London, Black individuals are about four times more likely to be stopped and searched than White individuals. Using data on stop and search events in London from January 2019 to December 2023, this paper aims to investigate disproportionality in the volume of stops for expressive crimes involving Black individuals compared to other ethnicities. We employ a semi-parametric partially linear structural regression method and introduce a Bayesian empirical likelihood procedure combined with double machine learning techniques to control for high-dimensional confounding and to accommodate strong prior assumptions. In addition, we show that the proposed procedure yields a valid posterior in terms of coverage. Applying this approach to the stop and search dataset, we find that racial disproportionality aimed at the Black community may be influenced by the borough racial composition when focusing on expressive crimes.
Racial bias in medicine, such as in dermatology, presents significant ethical and clinical challenges. This is likely to happen because there is a significant underrepresentation of darker skin tones in training datasets for machine learning models. While efforts to address bias in dermatology have focused on improving dataset diversity and mitigating disparities in discriminative models, the impact of racial bias on generative models remains underexplored. Generative models, such as Variational Autoencoders (VAEs), are increasingly used in healthcare applications, yet their fairness across diverse skin tones is currently not well understood. In this study, we evaluate the fairness of generative models in clinical dermatology with respect to racial bias. For this purpose, we first train a VAE with a perceptual loss to generate and reconstruct high-quality skin images across different skin tones. We utilize the Fitzpatrick17k dataset to examine how racial bias influences the representation and performance of these models. Our findings indicate that VAE performance is, as expected, influenced by representation, i.e. increased skin tone representation comes with increased performance
Digital ads on social-media platforms play an important role in shaping access to economic opportunities. Our work proposes and implements a new third-party auditing method that can evaluate racial bias in the delivery of ads for education opportunities. Third-party auditing is important because it allows external parties to demonstrate presence or absence of bias in social-media algorithms. Education is a domain with legal protections against discrimination and concerns of racial-targeting, but bias induced by ad delivery algorithms has not been previously explored in this domain. Prior audits demonstrated discrimination in platforms' delivery of ads to users for housing and employment ads. These audit findings supported legal action that prompted Meta to change their ad-delivery algorithms to reduce bias, but only in the domains of housing, employment, and credit. In this work, we propose a new methodology that allows us to measure racial discrimination in a platform's ad delivery algorithms for education ads. We apply our method to Meta using ads for real schools and observe the results of delivery. We find evidence of racial discrimination in Meta's algorithmic delivery of ads
Text-to-image generative AI models such as Stable Diffusion are used daily by millions worldwide. However, the extent to which these models exhibit racial and gender stereotypes is not yet fully understood. Here, we document significant biases in Stable Diffusion across six races, two genders, 32 professions, and eight attributes. Additionally, we examine the degree to which Stable Diffusion depicts individuals of the same race as being similar to one another. This analysis reveals significant racial homogenization, e.g., depicting nearly all Middle Eastern men as bearded, brown-skinned, and wearing traditional attire. We then propose debiasing solutions that allow users to specify the desired distributions of race and gender when generating images while minimizing racial homogenization. Finally, using a preregistered survey experiment, we find evidence that being presented with inclusive AI-generated faces reduces people's racial and gender biases, while being presented with non-inclusive ones increases such biases, regardless of whether the images are labeled as AI-generated. Taken together, our findings emphasize the need to address biases and stereotypes in text-to-image models
The manner in which different racial and gender groups are portrayed in news coverage plays a large role in shaping public opinion. As such, understanding how such groups are portrayed in news media is of notable societal value, and has thus been a significant endeavour in both the computer and social sciences. Yet, the literature still lacks a longitudinal study examining both the frequency of appearance of different racial and gender groups in online news articles, as well as the context in which such groups are discussed. To fill this gap, we propose two machine learning classifiers to detect the race and age of a given subject. Next, we compile a dataset of 123,337 images and 441,321 online news articles from New York Times (NYT) and Fox News (Fox), and examine representation through two computational approaches. Firstly, we examine the frequency and prominence of appearance of racial and gender groups in images embedded in news articles, revealing that racial and gender minorities are largely under-represented, and when they do appear, they are featured less prominently compared to majority groups. Furthermore, we find that NYT largely features more images of racial minority g
Fairness in deep learning models trained with high-dimensional inputs and subjective labels remains a complex and understudied area. Facial emotion recognition, a domain where datasets are often racially imbalanced, can lead to models that yield disparate outcomes across racial groups. This study focuses on analyzing racial bias by sub-sampling training sets with varied racial distributions and assessing test performance across these simulations. Our findings indicate that smaller datasets with posed faces improve on both fairness and performance metrics as the simulations approach racial balance. Notably, the F1-score increases by $27.2\%$ points, and demographic parity increases by $15.7\%$ points on average across the simulations. However, in larger datasets with greater facial variation, fairness metrics generally remain constant, suggesting that racial balance by itself is insufficient to achieve parity in test performance across different racial groups.
Racial disparities in healthcare expenditures are well-documented, yet the underlying drivers remain complex. This study develops a framework to decompose such disparities through shifts in the distributions of mediating variables, rather than treating race itself as a manipulable exposure. We define disparities as differences in covariate-adjusted outcome distributions across racial groups, and decompose the total disparity into a component attributable to differences in mediator distributions, and a residual component that remains after equalizing those distributions. Using data from the Medical Expenditures Panel Survey (MEPS), we examine the extent to which expenditure disparities would persist or be reduced if mediators such as socioeconomic status (SES), insurance access, health behaviors, or health status were equalized across racial groups. To ensure valid inference, we derive asymptotically linear estimators based on influence-function techniques and flexible machine learning, including super learners and a two-part model designed for the zero-inflated, right-skewed nature of expenditure data. Applying this framework to MEPS data from 2009 and 2016, substantial disparities
Computer vision is widely deployed, has highly visible, society altering applications, and documented problems with bias and representation. Datasets are critical for benchmarking progress in fair computer vision, and often employ broad racial categories as population groups for measuring group fairness. Similarly, diversity is often measured in computer vision datasets by ascribing and counting categorical race labels. However, racial categories are ill-defined, unstable temporally and geographically, and have a problematic history of scientific use. Although the racial categories used across datasets are superficially similar, the complexity of human race perception suggests the racial system encoded by one dataset may be substantially inconsistent with another. Using the insight that a classifier can learn the racial system encoded by a dataset, we conduct an empirical study of computer vision datasets supplying categorical race labels for face images to determine the cross-dataset consistency and generalization of racial categories. We find that each dataset encodes a substantially unique racial system, despite nominally equivalent racial categories, and some racial categories