Open AccessPosted Content
'It's Reducing a Human Being to a Percentage': Perceptions of Justice in Algorithmic Decisions
Reads0
Chats0
TLDR
There may be no 'best' approach to explaining algorithmic decisions, and that reflection on their automated nature both implicates and mitigates justice dimensions.Abstract:
Data-driven decision-making consequential to individuals raises important questions of accountability and justice. Indeed, European law provides individuals limited rights to 'meaningful information about the logic' behind significant, autonomous decisions such as loan approvals, insurance quotes, and CV filtering. We undertake three experimental studies examining people's perceptions of justice in algorithmic decision-making under different scenarios and explanation styles. Dimensions of justice previously observed in response to human decision-making appear similarly engaged in response to algorithmic decisions. Qualitative analysis identified several concerns and heuristics involved in justice perceptions including arbitrariness, generalisation, and (in)dignity. Quantitative analysis indicates that explanation styles primarily matter to justice perceptions only when subjects are exposed to multiple different styles --- under repeated exposure of one style, scenario effects obscure any explanation effects. Our results suggests there may be no 'best' approach to explaining algorithmic decisions, and that reflection on their automated nature both implicates and mitigates justice dimensions.read more
Citations
More filters
Posted Content
Manipulating and Measuring Model Interpretability
Forough Poursabzi-Sangdeh,Daniel G. Goldstein,Jake M. Hofman,Jennifer Wortman Vaughan,Hanna Wallach +4 more
TL;DR: A sequence of pre-registered experiments showed participants functionally identical models that varied only in two factors commonly thought to make machine learning models more or less interpretable: the number of features and the transparency of the model (i.e., whether the model internals are clear or black box).
Proceedings ArticleDOI
Questioning the AI: Informing Design Practices for Explainable AI User Experiences
TL;DR: An algorithm-informed XAI question bank is developed in which user needs for explainability are represented as prototypical questions users might ask about the AI, and used as a study probe to identify gaps between current XAI algorithmic work and practices to create explainable AI products.
Proceedings ArticleDOI
Improving fairness in machine learning systems: What do industry practitioners need?
TL;DR: In this article, the authors conduct a systematic investigation of commercial product teams' challenges and needs for support in developing fairer ML systems and identify areas of alignment and disconnect between the challenges faced by industry practitioners and solutions proposed in the fair ML research literature.
Posted Content
A Multidisciplinary Survey and Framework for Design and Evaluation of Explainable AI Systems
TL;DR: A framework with step-by-step design guidelines paired with evaluation methods to close the iterative design and evaluation cycles in multidisciplinary XAI teams is developed and summarized ready-to-use tables of evaluation methods and recommendations for different goals in XAI research are provided.
Proceedings ArticleDOI
Actionable Recourse in Linear Classification
TL;DR: An integer programming toolkit is presented to measure the feasibility and difficulty of recourse in a target population, and generate a list of actionable changes for a person to obtain a desired outcome, and illustrate how recourse can be significantly affected by common modeling practices.
References
More filters
Proceedings ArticleDOI
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
TL;DR: In this article, the authors propose LIME, a method to explain models by presenting representative individual predictions and their explanations in a non-redundant way, framing the task as a submodular optimization problem.
Book
The Social Psychology of Procedural Justice
E. Allan Lind,Tom R. Tyler +1 more
TL;DR: In this article, two models of procedural justice are presented: Procedural Justice in Law I and Procedural justice in Law II, and the Generality of Procedural Jurisprudence.
Journal ArticleDOI
Justice at the millennium: a meta-analytic review of 25 years of organizational justice research
TL;DR: It is suggested that although different justice dimensions are moderately to highly related, they contribute incremental variance explained in fairness perceptions and illustrate the overall and unique relationships among distributive, procedural, interpersonal, and informational justice and several organizational outcomes.
Journal ArticleDOI
Likert scales, levels of measurement and the "laws" of statistics.
TL;DR: It is shown that many studies, dating back to the 1930s consistently show that parametric statistics are robust with respect to violations of these assumptions, and parametric methods can be utilized without concern for “getting the wrong answer”.
Journal ArticleDOI
Comparing individual means in the analysis of variance.
TL;DR: A simple and definite procedure is proposed for dividing treatments into distinguishable groups, and for determining that the treatments within some of these groups are different, although there is not enough evidence to say "which is which."
Related Papers (5)
Reactions to Decisions with Uncertain Consequences: Reliance on Perceived Fairness versus Predicted Outcomes Depends on Knowledge
Kelly E. See,Kelly E. See +1 more