ARIADNE: Final Report on Data Mining. Wilcke, W., de Boer , V., van Harmelen , F., de Kleijn , M., Wansleeben, M., Dimitropoulos, H., & Wright, H. Ariadne, 2017.
abstract   bibtex   
Recent years have witnessed a growing interest from archaeological communities in Linked Data. ARIADNE, the AdvancedResearch Infrastructure for Archaeological Data set Networking in Europe, facilitates a central web portal that providesaccess to archaeological data from various sources. Parts of these data have been being published as Linked Data, andare currently available in the Linked Open Data cloud. With it, the nature of these data has shifted from unstructuredto structured. This presents new opportunities for data mining. While general-purpose software exists, recent studieshave revealed the importance of two domain-specific requirements: 1) produce interpretable results, and 2) allow trustin the underlying model. In this work, we investigate to what extend interpretable data mining can contribute to theunderstanding of linked archaeological data. A case study washeld, which involved the mining of semantic association rules over data sets of increasing levels of knowledgegranularity, followed by the qualitative evaluation of these rules by domain experts. Experiments have shown that theapproach yielded mostly plausible patterns, some of which were seen as highly relevant.
@book{fcb11c81af894034a33d5a6d705166b0,
  title     = "ARIADNE: Final Report on Data Mining",
  abstract  = "Recent years have witnessed a growing interest from archaeological communities in Linked Data. ARIADNE, the AdvancedResearch Infrastructure for Archaeological Data set Networking in Europe, facilitates a central web portal that providesaccess to archaeological data from various sources. Parts of these data have been being published as Linked Data, andare currently available in the Linked Open Data cloud. With it, the nature of these data has shifted from unstructuredto structured. This presents new opportunities for data mining. While general-purpose software exists, recent studieshave revealed the importance of two domain-specific requirements: 1) produce interpretable results, and 2) allow trustin the underlying model. In this work, we investigate to what extend interpretable data mining can contribute to theunderstanding of linked archaeological data. A case study washeld, which involved the mining of semantic association rules over data sets of increasing levels of knowledgegranularity, followed by the qualitative evaluation of these rules by domain experts. Experiments have shown that theapproach yielded mostly plausible patterns, some of which were seen as highly relevant.",
  author    = "W.X. Wilcke and {de Boer}, V. and {van Harmelen}, F.A.H. and {de Kleijn}, M.T.M. and M. Wansleeben and Harry Dimitropoulos and Holly Wright",
  year      = "2017",
  series    = "ARIADNE",
  publisher = "Ariadne",
  number    = "D16.3",
}

Downloads: 0