Historical research using digitized sources has gained great interest over the past years. It has been possible to digitize printed texts already for a while, yet handwritten materials have been much more difficult to utilize. Nevertheless, the situation is currently changing. The European READ Project, participated by the Finnish National Archives, has developed the Transkribus Program that can, for the time being, recognize up to 90% of handwritten text in a given data. For the first time, a large-scale digitization of handwritten sources is becoming sensible and useful.
In our project "Digital History and Handwritten Sources: Digitization, Machine-Reading and Historical Analysis of Wartime Letters" (DIGIKÄKI), we are doing digital humanities research on handwritten texts produced by ordinary people. Our data comprises of the largest single collection of personal writings in Finland, the wartime letter collection of the Tampere University Folklife Archives. At the moment, the collection includes about 60,000 letters written during World War II: writings by about 3,000 Finnish men and women from allover the country and from all social strata.
The project has two central aims:
(1) Digitization of the letters: We will photograph a large part of the collection, use the Transkribus Program to transform the letters to digitized texts and create a metadatabase for these letters. As a result, we will have a digital corpus of letters, which is exceptional in its size both in Finland and internationally. This process will greatly enhance the usability of this unique collection and its research in history as well as in other disciplines.
(2) Research: We will analyze the letters using new digital humanities research methods. Digitized letters will allow, for the first time, to study quantitatively how ordinary people's verbal and emotional expression changed during the war years of 1939-45. The data will also enable to study more general questions in digital historiography and in social and cultural history.
DIGIKÄKI is financed by the Jalmari Finne Foundation and it operates under the Academy of Finland Centre of Excellence in the History of Experiences (HEX). The project is led by Dr Ville Kivimäki.
Ilari Taskinen, Risto Turunen, Lauri Uusitalo & Ville Kivimäki (2021), “Religion, Patriotism and War Experience in Digitized Wartime Letters in Finland, 1939–44,” Journal of Contemporary History, published first online and available open access at https://doi.org/10.1177/00220094211066006.
Ilari Taskinen, Risto Turunen, Lauri Uusitalo & Ville Kivimäki (2021), “Digitalisoituva menneisyys: Käsinkirjoitettujen aineistojen konelukemisesta,” Alusta! Yhteiskunta- ja kulttuuritieteiden verkkolehti, online publication at https://www.tuni.fi/alustalehti/2021/10/08/digitalisoituva-menneisyys-kasinkirjoitettujen-aineistojen-konelukemisesta/, published 8 October 2021.
Free public Transkribus-model for the AI text recognition of handwritten Finnish text of the 1940s: https://readcoop.eu/model/finnish_world_war_ii_letters_and_diaries/