Where fairness fails: data, algorithms, and the limits of antidiscrimination discourse

@article{Hoffmann2019WhereFF,
  title={Where fairness fails: data, algorithms, and the limits of antidiscrimination discourse},
  author={Anna Lauren Hoffmann},
  journal={Information, Communication \& Society},
  year={2019},
  volume={22},
  pages={900 - 915}
}
  • A. Hoffmann
  • Published 13 May 2019
  • Sociology
  • Information, Communication & Society
ABSTRACT Problems of bias and fairness are central to data justice, as they speak directly to the threat that ‘big data’ and algorithmic decision-making may worsen already existing injustices. In the United States, grappling with these problems has found clearest expression through liberal discourses of rights, due process, and antidiscrimination. Work in this area, however, has tended to overlook certain established limits of antidiscrimination discourses for bringing about the change demanded… 
View on Taylor & Francis
static1.squarespace.com
174 Citations
Highly Influential Citations
15
Background Citations
99
Methods Citations
5
Results Citations
1

174 Citations

Citation Type

Citation Type

What is the point of fairness?
that making disability explicit in discussions of AI and fairness is urgent, as the quick, black-boxed nature of automatic decision making exacerbates the disadvantages that people with disabilities…
Algorithmic Fairness and Structural Injustice: Insights from Feminist Political Philosophy
TLDR
It is shown that algorithmic fairness does not accommodate structural injustices in its current scope and some steps are taken in developing the paradigm of ‘responsible algorithmmic fairness’ to correct for errors in theCurrent scope and implementation of algorithmic fairness.
Escaping the 'Impossibility of Fairness': From Formal to Substantive Algorithmic Fairness
TLDR
This paper argues that the dominant, “formal” approach to algorithmic fairness is ill-equipped as a framework for pursuing equality, as its narrow frame of analysis generates restrictive approaches to reform and proposes an alternative: a “substantive’ approach that centers opposition to social hierarchies and provides a more expansive analysis of how to address inequality.
Rethinking Fairness: An Interdisciplinary Survey of Critiques of Hegemonic ML Fairness Approaches
This survey article assesses and compares existing critiques of current fairness-enhancing technical interventions in machine learning (ML) that draw from a range of non-computing disciplines,…
What is the Point of Fairness? Disability, AI and The Complexity of Justice
TLDR
Two case studies from within computer vision are presented of technologies putatively intended to help disabled people but, through failures to consider structural injustices in their design, are likely to result in harms not addressed by a "fairness" framing of ethics.
What is the point of fairness?
TLDR
Two case studies from within computer vision - a subdiscipline of AI focused on training algorithms that can "see" - of technologies putatively intended to help disabled people but, through failures to consider structural injustices in their design, are likely to result in harms not addressed by a "fairness" framing of ethics.
Impossibility of What? Formal and Substantive Equality in Algorithmic Fairness
TLDR
This paper argues that the dominant, “formal” approach to algorithmic fairness is ill-equipped as a framework for pursuing equality, as its narrow frame of analysis generates restrictive approaches to reform and proposes an alternative: a "substantive" approach that centers opposition to social hierarchies and provides a more expansive analysis of how to address inequality.
The false promise of risk assessments: epistemic reform and the limits of fairness
TLDR
It is concluded that risk assessments are an ill-advised tool for challenging the centrality and legitimacy of incarceration within the criminal justice system and how algorithmic fairness narrows the scope of judgments about justice and how "fair" algorithms can reinforce discrimination.
On the apparent conflict between individual and group fairness
TLDR
This paper draws on discussions from within the fair machine learning research and from political and legal philosophy to argue that individual and group fairness are not fundamentally in conflict, and outlines accounts of egalitarian fairness which encompass plausible motivations for both group and individual fairness.
Studying up: reorienting the study of algorithmic fairness around issues of power
TLDR
This paper expands on Elish and Boyd's call for data scientists to develop more robust frameworks for understanding their work as situated practice by examining a specific methodological debate within the field of anthropology, frequently referred to as the practice of "studying up".
...
...

References

SHOWING 1-10 OF 111 REFERENCES
Fairness in Criminal Justice Risk Assessments: The State of the Art
Objectives: Discussions of fairness in criminal justice risk assessments typically lack conceptual precision. Rhetoric too often substitutes for careful analysis. In this article, we seek to clarify…
The Structural Turn and the Limits of Antidiscrimination Law
The notion of institutional racism or sexism has been around a long time. Many of the original drafters of the Civil Rights Act of 1964 sought to address more than just discrete acts of…
Social Injustice in Surveillance Capitalism
TLDR
This paper makes explicit how the practices inherent to what Shoshana Zuboff calls ‘surveillance capitalism’ are threats to social justice, based on the normative principle that they prevent parity of participation in social life.
Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness
TLDR
It is proved that the computational problem of auditing subgroup fairness for both equality of false positive rates and statistical parity is equivalent to the problem of weak agnostic learning, which means it is computationally hard in the worst case, even for simple structured subclasses.
Avoiding Discrimination through Causal Reasoning
TLDR
This work crisply articulate why and when observational criteria fail, thus formalizing what was before a matter of opinion and put forward natural causal non-discrimination criteria and develop algorithms that satisfy them.
Weapons of Math Destruction: How Big Data Increases Inequality and Threatens Democracy
TLDR
Tracing the arc of a persons life, ONeil exposes the black box models that shape the authors' future, both as individuals and as a society, in this urgent and necessary book.
Demarginalizing the Intersection of Race and Sex: A Black Feminist Critique of Antidiscrimination Doctrine, Feminist Theory and Antiracist Politics
One of the very few Black women's studies books is entitled All the Women Are White; All the Blacks Are Men, But Some of Us are Brave.1 I have chosen this title as a point of departure in my efforts…
Technological Due Process
Distinct and complementary procedures for adjudications and rulemaking lie at the heart of twentieth-century administrative law. Due process required agencies to provide individuals notice and an…
Normal Life: Administrative Violence, Critical Trans Politics, and the Limits of Law
Revised and Expanded Edition Wait—what's wrong with rights ? It is usually assumed that trans and gender nonconforming people should follow the civil rights and "equality" strategies of lesbian and…
The Content of Our Categories: A Cognitive Bias Approach to Discrimination and Equal Employment Opportunity
Title VII's disparate treatment model of discrimination is premised on the notion that intergroup bias is motivational in origin. This premise, in turn, is based on a number of assumptions regarding…
...
...