Item ranking systems support users in multi-criteria decision-making tasks. Users need to trust rankings and ranking algorithms to reflect user preferences nicely while avoiding systematic errors and biases. However, today only few approaches help end users, model developers, and analysts to explain rankings. We report on the study of explanation approaches from the perspectives of recommender systems, explainable AI, and visualization research and propose the first cross-domain design space for explainers of item rankings. In addition, we leverage the descriptive power of the design space to characterize a) existing explainers and b) three main user groups involved in ranking explanation tasks. The generative power of the design space is a means for future designers and developers to create more target-oriented solutions in this only weakly exploited space.

翻译：项目排名系统支持用户执行多标准决策任务。 用户需要信任排名和排序算法,以很好地反映用户偏好,同时避免系统性错误和偏差。 但是,今天只有少数方法帮助终端用户、模型开发者和分析家解释排名。 我们报告从推荐者系统、可解释的AI和可视化研究的角度对解释方法的研究,并提议项目排名解释者的第一个跨域设计空间。 此外,我们利用设计空间的描述性能力来描述(a) 现有解释者和(b) 参与排名解释任务的三个主要用户群体。设计空间的突变能力是未来设计者和开发者在这一仅受到薄弱利用的空间创造更有针对性的解决方案的一种手段。