The feasibility of machine-learning based workflows for editing serial historical sources : First results of the Schenkenschans customs registers project

Faculty/Professorship: Digital History  
Author(s): Scheltjens, Werner  
Publisher Information: Bamberg : Otto-Friedrich-Universität
Year of publication: 2023
Pages: 1-16
Language(s): English
Forthcoming in: Machine learning and data mining for digital scholarly editions / Ulrike Henny-Krahmer (ed.): Norderstedt 2023
DOI: 10.20378/irb-58260
Licence: Creative Commons - CC BY-NC - Attribution - NonCommercial 4.0 International 
This paper discusses preliminary results of a project that aims to facilitate the study of logistics patterns in German-Dutch transport and trade on the Rhine in the early modern period by means of a digital edition of the customs registers of the Schenkenschans (SSZ). Based on an ongoing pilot study with a sample of the SSZ registers, the paper discusses the use of machine-learning based tools for HTR as starting point for creating a digital scholarly edition of serial historical sources. Building on a conceptualizing of the customs registrations in the SSZ as economic movement data, the paper briefly outlines how the scholarly edition supports data mining and documentation. Based on rigorous timing of the different steps in the proposed workflow, the pilot study assesses the feasibility of ML-based tools for HTR as a first step in the production of a digital scholarly edition of the SSZ for data mining and documentary purposes.
GND Keywords: Schenkenschanz; Zoll; Verzeichnis; Digitalisierung; Edition; Maschinelles Lernen
Keywords: Handwritten Text Recognition, Feasibility, Digital Scholarly Editing
DDC Classification: 940 History of Europe  
RVK Classification: NW 3960   
Type: Preprint
Release Date: 27. February 2023
Project: Digitale Erschließung einer seriellen Quelle für die niederländisch-deutsche Rheinschifffahrt in der Frühen Neuzeit: Pilotstudie über die Zollregister von der Schenkenschanz (1630-1810), von der automatischen Handschrifterkennung bis zur Online Datenbank.

File Description SizeFormat  
fisba58260.pdf507.51 kBPDFView/Open