Human language technology developed and used in CLARIN demonstrator projects WAHSP and BILAND supports advanced forms of (multi-lingual) text mining of large datasets of newspapers. We argue that the combination of exploratory search and text mining o ers an innovative research approach to systematically set up search trails in the historical sciences. We describe the development, use, and methodological challenges of the WAHSP and BILAND text-mining tools and the successor tool, Texcavator, to support alternating forms of distant reading and close reading in newspaper collections. We will show how semantic text mining speeds up the heuristic process and thus helped to provide new and challenging perspectives on the circulation of ideas and notions regarding drugs and eugenics in Dutch newspapers in the rst four decades of the 20th century.
IntroductionHistorical scholars are increasingly applying computational tools and methods to all phases of their research. Digital tools are used to open, present, and curate textual and multi-media sources in semantic text mining, for integration of geospatial information data, for various forms of visualisation, and for enhanced and multi-media publication of research results, blogs, and wikis. Digital history is a methodological approach that is framed by these digital tools' ability to make, de ne,