A global taxonomy of interpretable AI: unifying the terminology for the technical and social sciences

Since its emergence in the 1960s, Artificial Intelligence (AI) has grown to conquer many technology products and their fields of application. Machine learning, as a major part of the current AI solutions, can learn from the data and through experience to reach high performance on various tasks. This growing success of AI algorithms has led to a need for interpretability to understand opaque models such as deep neural networks. Various requirements have been raised from different domains, together with numerous tools to debug, justify outcomes, and establish the safety, fairness and reliability of the models. This variety of tasks has led to inconsistencies in the terminology with, for instance, terms such as interpretable, explainable and transparent being often used interchangeably in methodology papers. These words, however, convey different meanings and are "weighted" differently across domains, for example in the technical and social sciences. In this paper, we propose an overarching terminology of interpretability of AI systems that can be referred to by the technical developers as much as by the social sciences community to pursue clarity and efficiency in the definition of regulations for ethical and reliable AI development. We show how our taxonomy and definition of interpretable AI differ from the ones in previous research and how they apply with high versatility to several domains and use cases, proposing a-highly needed-standard for the communication among interdisciplinary areas of AI.

Coping with precarity during COVID-19: A study of platform work in Poland

This article explores how the COVID-19 pandemic has affected the work and life experiences of platform workers' and how workers have responded to the outbreak in Poland. Platform workers have been exposed to substantial fluctuations of demand during the pandemic, magnifying the distortions existing in an unregulated asymmetrical employment relationship diverging from the standard employment relationship. Findings illustrate how workers have attempted to reduce the disruptions underpinning the existence of this unregulated asymmetrical relationship by adopting different strategies, which resemble Hirschman's typology of loyalty, voice and exit. We explain the choice of strategies by highlighting workers' different access to resources and institutional capabilities, as well as by variation in their orientations.