论文标题
可解释排名和排名模型的设计空间
A Design Space for Explainable Ranking and Ranking Models
论文作者
论文摘要
项目排名系统在多标准决策任务中为用户提供支持。用户需要信任排名和排名算法，以很好地反映用户偏好，同时避免系统的错误和偏见。但是，如今，只有很少的方法可以帮助最终用户，模型开发人员和分析师解释排名。我们从推荐系统，可解释的AI和可视化研究的角度报告了解释方法的研究，并提出了第一个用于解释项目排名的跨域设计空间。此外，我们利用设计空间的描述能力来表征a）现有解释器和b）参与排名说明任务的三个主要用户组。设计空间的生成力量是将来的设计师和开发人员在仅在这个弱被利用的空间中创建更面向目标的解决方案的一种手段。
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.
