Given the problems of uncertainty and vagueness we argue that it is appropriate to use Text Mining methods to the semantic analysis of historical texts.
After addressing the challenges of historical spelling variants and OCR errors, we show that document classification attains high accuracy, and that the feature weights can be interpreted historically and linguistically, although with a high level of noise. Further, we were surprised how accurately topic models allow us to trace socio-historical changes, for example the change from scholastic thinking to empirical science in medical studies, and how professional health care replaced medieval quackery. Conceptual maps using kernel density estimation also led to clear results, with the disadvantage that topics are less clearly apparent. Both of these approaches are robust to parameter details, as long as stopword lists are used and OCR errors or historical spelling variants are addressed. Our results on using fasttext are mixed, however. ...
Job advertisements disappear in the Federal Gazette over time.
Given that each method has its strengths and its idiosyncrasies, applying a broad variety of quantitative approaches and being able to compare and inspect the different outputs