• Attributing Authorship in the Noisy Digitized Correspondence of Jacob and Wilhelm Grimm

    Author(s):
    Joanna Byszuk, Greta Franzini (see profile) , Emily Franzini, Melina Jander, Mike Kestemont, Jeremi Ochab, Gabriela Rotari, Jan Rybicki
    Date:
    2018
    Group(s):
    Digital Humanists, Textual Scholarship
    Subject(s):
    Authorship, Library materials--Digitization, Archival materials--Digitization, German literature, Optical character recognition
    Item Type:
    Article
    Tag(s):
    Brothers Grimm, Authorship attribution, Digitisation, OCR
    Permanent URL:
    http://dx.doi.org/10.17613/M6PS1N
    Abstract:
    This article presents the results of a multidisciplinary project aimed at better understanding the impact of different digitization strategies in computational text analysis. More specifically, it describes an effort to automatically discern the authorship of Jacob and Wilhelm Grimm in a body of uncorrected correspondence processed by HTR (Handwritten Text Recognition) and OCR (Optical Character Recognition), reporting on the effect this noise has on the analyses necessary to computationally identify the different writing style of the two brothers. In summary, our findings show that OCR digitization serves as a reliable proxy for the more painstaking process of manual digitization, at least when it comes to authorship attribution. Our results suggest that attribution is viable even when using training and test sets from different digitization pipelines. With regards to HTR, this research demonstrates that even though automated transcription significantly increases the risk of text misclassification when compared to OCR, a cleanliness above ≈ 20% is already sufficient to achieve a higher-than-chance probability of correct binary attribution.
    Metadata:
    Published as:
    Journal article    
    Status:
    Published
    Last Updated:
    5 years ago
    License:
    All Rights Reserved
    Share this:

    Downloads

    Item Name: pdf bbf15905-8886-458c-8eab-b6246e70f763.pdf
      Download View in browser
    Activity: Downloads: 544