A plea for an upgrade to the digital craft of the historian and digital methodology for discovering the past

TL;DR

The paper advocates for upgrading digital methods in history by integrating AI and neural networks to better interpret digitized historical sources, emphasizing collaboration among historians and data scientists.

Contribution

It proposes a new approach for historians to utilize AI and neural networks, moving beyond simple digitization to meaningful interpretation of historical data.

Findings

AI tools like Transkribus can infer meaning from digitized sources

Historians need to develop primary ontologies for digital text

Collaboration across disciplines enhances digital historical research

Abstract

This essay aims to bid analogue historians assume that digitisation is the first step to creating historical heritage based on the new language of Science: Computer Science. As we know, Humanities disciplines cannot easily be encapsulated in a few understandable numbers and names. However, historians must boost Artificial Intelligence (such as Transkribus) and Neural Networks to let the Machine infer meaning from the digitised historical primary source and become the most powerful tool to help historians understand what happened in the Past. Historians (collaborating with data scientists, expert annotators, librarians, archivists, and others, who are crucial to the successful management of digital data collection) have to create the primary ontology, starting from coding manuscripts into digital text, as the Biscari Archive (Italy) study case.