A Research Toolbox: A Complete Suite for Analysis in Digital Humanities

Abstract

The Georg Eckert Institute conducts applied, interdisciplinary research into textbooks and educational media, owning an important digitalized document corpus. Current Digital Libraries technologies don’t allow its researchers to fully exploit the potential offered by Natural Language Processing technologies, thus a new platform, based on open source solution, has been realized with the aim to offer a set of tools to the researchers, allowing them to adapt the research process to the single case without predefining a workflow. The system offers functionalities that allow text digitalization, OCR, language recognition, digital libraries management, topic modelling, word counting, text enrichment and specific reporting elements, all in a flexible and high scalable architecture.