FAIR-DS

Abstract

The use of artificial intelligence (AI) applications in a growing number of domains in recent years has put into focus the ethical, legal, and societal aspects (ELSA) of these technologies and the relevant challenges they pose. In this paper, we propose an ELSA curriculum for data scientists aiming to raise awareness about ELSA challenges in their work, provide them with a common language with the relevant domain experts in order to cooperate to find appropriate solutions, and finally, incorporate ELSA in the data science workflow. ELSA should not be seen as an impediment or a superfluous artefact but rather as an integral part of the Data Science Project Lifecycle. The proposed curriculum uses the CRISP-DM (CRoss-Industry Standard Process for Data Mining) model as a backbone to define a vertical partition expressed in modules corresponding to the CRISP-DM phases. The horizontal partition includes knowledge units belonging to three strands that run through the phases, namely ethical and societal, legal and technical rendering knowledge units (KUs). In addition to the detailed description of the aforementioned KUs, we also discuss their implementation, issues such as duration, form, and evaluation of participants, as well as the variance of the knowledge level and needs of the target audience.

Abstract

The explosion of data-driven applications using Artificial Intelligence (AI) in recent years has given rise to a variety of ethical issues regarding data collection, annotation, and processing using mostly opaque algorithms, as well as the interpretation and employment of the results of the AI pipeline. The ubiquity of AI applications negatively impacts a variety of sensitive areas, ranging from discrimination against vulnerable populations to privacy invasion and the environmental cost that these algorithms entail, and puts into focus on the ever present domain of AI ethics. In this review article we present a bird’s eye view approach of the AI ethics landscape, starting from a historical point of view, examining the moral issues that were introduced by big datasets and the application of non-symbolic AI algorithms, the normative approaches (principles and guidelines) to these issues and the ensuing criticism, as well as the actualization of these principles within the proposed frameworks. Subsequently, we focus on the concept of responsibility, both as personal responsibility of the AI practitioners and sustainability, meaning the promotion of beneficence for both the society and the domain, and the role of professional certification and education in averting unethical choices. Finally, we conclude with indicating the multidisciplinary nature of AI ethics and suggesting future challenges.