Enabling Case-Based Reasoning on the Web of Data

While Case-based reasoning (CBR) has successfully been deployed on the Web, its data models are typically inconsistent with existing information infrastructure and standards. In this paper, we examine how CBR can operate on the emerging Web of Data, with mutual benefits. The expense of knowledge engineering and curating a case base can be reduced by using Linked Data from the Web of Data. While Linked Data provides experiential data from many different domains, it also contains inconsistencies, missing data and noise which provide challenges for logic-based reasoning. CBR is well suited to provide alternative and robust reasoning approaches. We introduce (i) a lightweight CBR vocabulary which is suited for the open ecosystem of the emerging Web of Data, and provide (ii) a detailed example of a case base using data from multiple sources. We propose that for the first time the Web of Data provides data and a real context for open CBR systems.