Exploring the applicability of digital humanities tools to Ottoman and Turkish languages

Abstract The first known computerised language and literature analysis was carried out by Father Roberto Busa in 1949; such studies have increased greatly after 1980, and today the tools are diversified with artificial intelligence. Unfortunately, except for a few minor studies, this development cannot be seen in the fields of Turkish and Ottoman languages. Therefore, as the first step in producing tools for Turkish and Ottoman, it is necessary to understand the algorithms of existing English-based tools and determine the applicability of these algorithms to the Turkish and Ottoman languages. In this study, twelve tools based on text and network analysis will be examined in terms of their suitability for Turkish and Ottoman. Tests on the tools will be evaluated under the headings of Corpus, Visualisation, Word Count, N-Grams, Structure Analysis, Network Analysis, and Labelling. The data obtained will be evaluated in terms of the suitability of the algorithms of the tools, and suggestions will be made for the algorithms that seem suitable for the Turkish and Ottoman language and literature analysis tool or tools to be developed in the future.