This paper discusses educating stakeholders of algorithmic systems (systems that apply Artificial Intelligence/Machine learning algorithms) in the areas of algorithmic fairness, accountability, transparency and ethics (FATE). We begin by establishing the need for such education and identifying the intended consumers of educational materials on the topic. We discuss the topics of greatest concern and in need of educational resources; we also survey the existing materials and past experiences in such education, noting the scarcity of suitable material on aspects of fairness in particular. We use an example of a college admission platform to illustrate our ideas. We conclude with recommendations for further work in the area and report on the first steps taken towards achieving this goal in the framework of an academic graduate seminar course, a graduate summer school, an embedded lecture in a software engineering course, and a workshop for high school teachers.

In light of the widespread use of algorithmic (intelligent) systems across numerous domains, there is an increasing awareness about the need to explain their underlying decision-making process and resulting outcomes. Since oftentimes these systems are being considered as black boxes, adding explanations to their outcomes may contribute to the perception of their transparency and, as a result, increase users' trust and fairness perception towards the system, regardless of its actual fairness, which can be measured using various fairness tests and measurements. Different explanation styles may have a different impact on users' perception of fairness towards the system and on their understanding of the outcome of the system. Hence, there is a need to understand how various explanation styles may impact non-expert users' perceptions of fairness and understanding of the system's outcome. In this study we aimed at fulfilling this need. We performed a between-subject user study in order to examine the effect of various explanation styles on users' fairness perception and understanding of the outcome. In the experiment we examined four known styles of textual explanations (case-based, demographic-based, input influence-based and sensitivity-based) along with a new style (certification-based) that reflect the results of an auditing process of the system. The results suggest that providing some kind of explanation contributes to users' understanding of the outcome and that some explanation styles are more beneficial than others. Moreover, while explanations provided by the system are important and can indeed enhance users' perception of fairness, their perception mainly depends on the outcome of the system. The results may shed light on one of the main problems in explainability of algorithmic systems, which is choosing the best explanation to promote users' fairness perception towards a particular system, with respect to the outcome of the system. The contribution of this study is reflected in the new and realistic case study that was examined, in the creation and evaluation of a new explanation style that can be used as the link between the actual (computational) fairness of the system and users' fairness perception and in the need of analyzing and evaluating explanations while taking into account the outcome of the system.

Algorithms play an increasing role in our everyday lives. Recently, the harmful potential of biased algorithms has been recognized by researchers and practitioners. We have also witnessed a growing interest in ensuring the fairness and transparency of algorithmic systems. However, so far there is no agreed upon solution and not even an agreed terminology. The proposed research defines the problem space, solution space and a prototype of comprehensive framework for the detection and reducing biases in algorithmic systems.

No abstract

Mitigating bias in algorithmic systems is a critical issue drawing attention across communities within the information and computer sciences. Given the complexity of the problem and the involvement of multiple stakeholders—including developers, end users, and third-parties—there is a need to understand the landscape of the sources of bias, and the solutions being proposed to address them, from a broad, cross-domain perspective. This survey provides a “fish-eye view,” examining approaches across four areas of research. The literature describes three steps toward a comprehensive treatment—bias detection, fairness management, and explainability management—and underscores the need to work from within the system as well as from the perspective of stakeholders in the broader context.