Historical Models and Serial Sources
Serial sources such as records, registers, and inventories are the ‘classic’ sources for quantitative history. Unstructured, narrative texts such as newspaper articles or reports were out of reach for historical analyses, both for practical reasons — availability, time needed for manual processing — and for methodological reasons: manual coding of texts is notoriously difficult and hampered by low inter-coder reliability. The recent availability of large amounts of digitized sources allows for the application of natural language processing, which has the potential to overcome these problems. However, the automatic evaluation of large amounts of texts — and historical texts in particular — for historical research also brings new challenges. First of all, it requires a source criticism that goes beyond the individual source and also considers the corpus as a whole. It is a well-known problem in corpus linguistics to determine the ‘balancedness’ of a corpus, but when analyzing the content of texts rather than ‘just’ the language, determining the ‘meaningfulness’ of a corpus is even more important. Second, automatic analyses require operationalizable descriptions of the information you are looking for. Third, automatically produced results require interpretation, in particular, when — as in history — the ultimate research question is qualitative, not quantitative. This, finally, poses the question, whether the insights gained could inform formal, i.e., machine-processable, models, which could serve as foundation and stepping stones for further research.
Copyright (c) 2019 Michael Piotrowski
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).