Exploring Discrimination: A User-centric Evaluation of Discrimination-Aware Data Mining

24 citations recorded by the source corpus.

How researchers see this paper

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

Fairwashing: the risk of rationalization (2019, methodology): “Possible exceptions include AI Fairness 360 that provides visualizations of attribute bias and feature bias localization [5], DCUBE-GUI [6] that has an interface for visualizing the unfairness scores of association rules resulted from data mining as well as FairML [1] that computes the relative impo”
European Union Regulations on Algorithmic Decision-Making and a "Right to Explanation" (2016, background): “Furthermore, a number of recent studies have attempted to tackle the issue of discrimination within algorithms by introducing tools to both identify (Berendt & Preibusch, 2012; Sandvig et al., 2014) and rectify (Calders & Verwer, 2010; Hajian et al., 2011; Zliobaite et al., 2011; Berendt &…”
Better decision support through exploratory discrimination-aware data mining: foundations and empirical evidence (2014, methodology): “Where applicable, we will focus on the European ‘‘Gender Directive’’ 2004/113/EC (EU 2004) because its 1 Sections 2 and 3.1–3.3 extend on a previous workshop paper (Berendt and Preibusch 2012), and Sect.”
Discrimination-aware data mining: a survey (2017, methodology): “DCUBE-GUI tool is further extended by Berendt and Preibusch (2012), where a user of the tool is involved while exploring or inspecting discrimination further.”