Data Science as Political Action: Grounding Data Science in a Politics of Justice

By Ben Green. 2018

132 citations recorded by the source corpus.

In response to recent controversies, the field of data science has rushed to adopt codes of ethics. Such professional codes, however, are ill-equipped to address broad matters of social justice. Instead of ethics codes, I argue, the field must embrace politics. Data scientists must recognize themselves as political actors engaged in normative constructions of society and, as befits political work, evaluate their work according to its downstream material impacts on people's lives. I justify this notion in two parts: first, by articulating why data scientists must recognize themselves as political actors, and second, by describing how the field can evolve toward a deliberative and rigorous grounding in a politics of social justice. Part 1 responds to three arguments that are commonly invoked by data scientists when they are challenged to take political positions regarding their work. In confronting these arguments, I will demonstrate why attempting to remain apolitical is itself a political stance--a fundamentally conservative one--and why the field's current attempts to promote "social good" dangerously rely on vague and unarticulated political assumptions. Part 2 proposes a framework for what a politically-engaged data science could look like and how to achieve it, recognizing the challenge of reforming the field in this manner. I conceptualize the process of incorporating politics into data science in four stages: becoming interested in directly addressing social issues, recognizing the politics underlying these issues, redirecting existing methods toward new applications, and, finally, developing new practices and methods that orient data science around a mission of social justice. The path ahead does not require data scientists to abandon their technical expertise, but it does entail expanding their notions of what problems to work on and how to engage with society.

Subfields: Cognitive Neuroscience, Public Health, Environmental and Occupational Health, Safety Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Public Health, Environmental and Occupational Health

In Safety Research

Citations in the corpus

Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries (2019, methodology): “…to implement research outcomes should involve those that may be aﬀected or whose data is being used (Costanza-Chock, 2018; Design Justice, 2018; Green, 2018)—following the “ nothing about us without us ” principle stating that no policy should be enacted without the direct participation of all…”
Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection (2021, background): “In general, we urge people to embrace that each design decision has socio-political implications (Green, 2020; Cambo, 2021), and encourage them to develop technologies to shift power to the targets of oppression (Blodgett et al., 2020; Kalluri, 2020; Birhane, 2021).”
The Principles and Limits of Algorithm-in-the-Loop Decision Making (2019, background): “…assessments have the potential to improve decision making, but can also lead to unintended outcomes as they are integrated into human decision making processes and broader political contexts; evaluations must therefore be grounded in rigorous sociotechnical analyses of the downstream impacts [35].”
Artificial Intelligence and Journalism (2019, background): “Acknowledging the political nature of seemingly objective choices in building AI systems is an important first step (Green, 2018).”
Confronting Power and Corporate Capture at the FAccT Conference (2022, background): “ward political action [27, 48, 65], resistance [30, 68], and justice [14].”
Evaluation Gaps in Machine Learning Practice (2022, background): “Changes to the ecosystem itself—e.g., addressing what social change is perceived as possible and desirable [49, 68, 79]—are assumed to be out of scope, as are concerns for setting of precedents for other ML developers.”
The false promise of risk assessments: epistemic reform and the limits of fairness (2020, background): “Instead, an algorithm’s fairness is treated as determinative of it having fair social impacts; as long as risk assessments can lead to more accurate or fair decisions, the thinking goes, they are a step in the right direction [11, 58, 155].”
Algorithmic realism: expanding the boundaries of algorithmic thought (2020, background): “e orts that are motivated as contributions to “social good” typically lack a clear explanation of what such “good” entails, instead relying on vague and unde ned notions [50].”