A Link to the Past: Text Mining and Entity Reconciliation with the Digital Index of North American Archaeology (DINAA)

Part of: Society for American Archaeology 82nd Annual Meeting, Vancouver, BC (2017)

The Digital Index of North American Archaeology (DINAA) provides a continuously expanding open source gazetteer of archaeological data from governmental site file inventories across North America. While visualizing spatial distributions of commonly recorded archaeological attributes across modern municipal boundaries alone can provide unique insights into the past, the expansive utility of an open and linked infrastructure is realized when data are coupled to other Web-enabled information systems. Text mining, entity reconciliation, and unique identifiers allow DINAA to interface with publications, archives, museums, scientific journals, and web-enabled genetic datasets. This poster symposium focuses on using DINAA to create and visualize these links to the past with specific examples, including text mining of American Antiquity through JSTOR, and linking archaeological records to published information on ancient DNA datasets through the National Center for Biotechnology Information. The current state of DINAA will be reported with maps and metrics detailing up-to-date North American coverage.