A Digital Edition between Stylometry and OCR: The Klagenfurter Ausgabe of Robert Musil
Article Sidebar
Main Article Content
Abstract
This article presents the digital edition of Robert Musil’s work (Klagenfurter Ausgabe) and its role in a digital humanities project aimed at reconstructing Musil’s activity in the WWI journal Tiroler Soldaten-Zeitung. First, the article reviews the ways in which the compu- tational methods of stylometry are applied to attribute the anonymous texts published in the Klagenfurter Ausgabe. Second, it explores how optical character recognition (OCR) soft- ware is employed to expand the corpus. At the core of this methodology two machine learn- ing algorithms are trained and revised using the transcriptions of the Klagenfurter Ausgabe, to reach an accuracy of about 99.9% in the digitization of the Tiroler Soldaten-Zeitung texts. The work of this project offers not only the possibility of expanding stylometric analysis to the whole journal, but also of improving the transcriptions of the Klagenfurter Ausgabe.
Downloads
Article Details
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 (see:http://creativecommons.org/licenses/by/3.0/us/) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors warrant that their submission is their own original work, and that they have the right to grant the rights contained in this license. Authors also warrant that their submission does not, to the best of your knowledge, infringe upon anyone's copyright. If the submission contains material for which an author does not hold the copyright, authors warrant that they have obtained the unrestricted permission of the copyright owner to grant Indiana University the rights required by this license, and that such third-party owned material is clearly identified and acknowledged within the text or content of their submission.
- 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 acknowledgment of its initial publication in this journal.