DigiTS

The Center for Digital Text Scholarship (DigiTS) is a project with a focus on textual data, funded by the European Union. Bringing in a dedicated team of experts, it will enable several key actions. Firstly, DigiTS will be able to focus on research activities, including the promotion and development of LLMs for Estonian. Secondly, concerning teaching and training, DigiTS will expand studies in Digital Humanities at all levels of higher education. Thirdly, as a result of the previous points, DigiTS will have a stronger basis for collaboration with other institutes at UT as well as with GLAM institutions (galleries, libraries, archives, museums) and start-ups in the industry. Since text-based DH is related to many fields in the humanities and social sciences, DigiTS will increase the ability to apply digital methods to textual data relevant to a multitude of scientific disciplines.

The project revolves around the following objectives:

• Establishing an excellent international research team for DigiTS, in line with the European Charter for Researchers and Code of Conduct for the Recruitment of Researchers.
• Conducting excellent internationally visible research in text-based Digital Humanities (DH) in collaboration with related institutes at the Faculty of Art and Humanities and the Faculty of Social Sciences at UT.
• Improving the quality and diversity of DH teaching and support at UT, training future DH scholars, helping collaborating units in implementing computational methods for text analysis and educating future GLAM professionals.
• Contributing to the development and management of the text-based data infrastructure for LLMs, bringing expertise in text analysis routines for under-resourced languages, such as Estonian, as well as non-standard language variants.
• Ensuring the sustainability of DigiTS results by supporting new projects and new project proposals that will emerge at the Center.

The DigiTS research strategy will focus on developing cutting-edge methodology in computer-assisted text analysis, in order to address research questions of text similarity, intertextuality, information flow between texts, and so forth. These questions are routinely asked in the fields of information search and retrieval, data analysis, classification, forensic textual studies, computational literary studies, and many others. However, the relevant data landscape – with the Estonian language as a pilot case – is significantly scarcer and more complex than in typical applications, therefore the DigiTS team will have to face challenges concerning data acquisition, data enhancement and data analysis.

Follow our website and our account on Bluesky.

Image