Unlocking the Schematismus: A Machine Learning and Data-driven Approach Toward Mapping Habsburg Middle Class in the Long 19th Century

The Habsburg Schematismus, an annual directory listing all civil servants of the Habsburg Monarchy, represents a unique historical source. Between 1780 and 1918, it recorded hundreds of thousands of people employed in state service. These individuals formed the backbone of an emerging middle class in Central Europe. However, their biographies, careers, and networks have remained largely unexplored. An international research team will now employ cutting-edge technologies to make this valuable historical data accessible to scholars and the public. Using artificial intelligence and machine learning, the scanned pages of the Schematismus will be automatically processed and the information they contain transformed into a searchable database. This new digital resource will enable, for the first time, systematic research into the social development of the Habsburg middle class. Of particular interest are questions of social and spatial mobility: How did individuals achieve social advancement? What role did education, marriage, or relationship networks play? How did civil servants move through the vast Habsburg Empire during their careers? Analysis of this data promises new insights into Central European society in the 19th century. The five-year project brings together experts from history, digital humanities, and computer science. Beyond the technical processing of the source material, new methods will be developed to automatically analyze large historical datasets. The resulting insights and tools will be made freely available to the scholarly community and interested public. This groundbreaking collaboration will not only illuminate an important chapter in European social history but also advance our ability to extract meaningful information from historical sources using digital methods. The project will break new ground when it comes to demonstrate the potential of data-driven historical research.