Joris van Eijnatten and Jaap Verheul develop digital tool to investigate the histories of concepts

Citizenship, democracy, freedom: when were these concepts incorporated in historical discourses? And what different meanings have been ascribed to these and other major concepts throughout the years? Cultural historians Prof. Joris van Eijnatten and Dr Jaap Verheul will develop a repurposable tool that enables humanities researchers to mine the historical development of concepts and the vocabulary with which they are expressed in big textual data repositories. This project, entitled 'Mining Shifting Concepts through Time (ShiCo): Word Vector Text Mining Change and Continuity in Conceptual History' has received a funding of 50.000 euros from the Netherlands eScience Center (NLeSC).

Conceptual change and continuity

Historical concepts (such as citizenship, democracy, evolution, health, liberty, security, trust, etc.) are essential to our understanding of the past. The history of concepts is a well-established field of research for historians, philosophers and linguists alike. However, there is little agreement on the nature of conceptual change, continuity and replacement, or on the proper methodology to distinguish between core concepts and the marginal vocabularies that are attached to them in certain historical contexts.

Core and marginal concepts

Therefore, Van Eijnatten, Verheul and their team aim to develop a digital tool that enables humanities researchers to mine the histories of concepts. Recent research suggests that vector representations derived by neural network language models offer new possibilities for obtaining high quality semantic representations from huge data sets.

Digitised repositories of historical newspapers and magazines are examples of examples of such data sets, which offer crucial empirical data to explore our historical heritage. Produced and controlled by social 'gatekeepers' such as journalists, editors and publishers, and information-rich and audience-oriented as they are, these media archives reflect and mediate public opinion in the societies that produce them.

The ShiCo team aims to deploy this material to mine changing vocabularies that are used to articulate historical concepts in public discourse. This does not only allow humanities scholars to assess conceptual stability, change and replacement, but also to distinguish between core concepts and the marginal associations that are attached to them in certain historical contexts.

New and improved cultural mining tool

The ShiCo team strives to develop a tool that can visualise historically embedded cultural concepts in a way that enables scholars to trace their specific historicity and their changes and continuities in meaning. For the first time, historians will be able to map integrally the intellectual concepts that structure public debates, forming the basis of broadly shared mentalities and worldviews.

ShiCo will further build on and go beyond the state-of-the-art that has already been achieved in the Texcavator project, an innovative text mining tool developed by scholars of Utrecht University and the University of Amsterdam (amongst which were Verheul and Eijnatten). ShiCo will be released as open source under Apache License, Version 2.0. New features will be:

• algorithms for contextual concept mining (Big Data Analytics/ Efficient Computing);
• advanced forms to visualise these word vectors (Big Data Analytics);
• robust and flexible database scalability that enables real-time analytics and visualisation of big data repositories simultaneously by teams (>15-100) of humanities scholars (Optimized Data Handling).

Project members

The ShiCo team consists of the following members:

• Prof. Joris van Eijnatten (Project leader and cultural historian, UU)
• Dr Jaap Verheul (Daily guidance and cultural historian, UU)
• Prof. Toine Pieters (Digital Humanities expert, daily guidance, UU)
• Prof. Maarten de Rijke (Information retrieval, University of Amsterdam)
• Prof. Charles van den Heuvel (Digital Humanities expert, dissemination, Huygens ING)
• Tom Kenters MA (Computer scientist, algorithm development, University of Amsterdam)
• Two NLeSC research engineers

About the NLeSC

The NLeSC connects scholars from different fields with specialists in eScience, a developing discipline that provides domain overarching software instruments (software, workflows and protocols) to support academic initiatives. The ShiCo team has received a funding of 50.000 euros via the NLeSC's Open Call for Path-Finding Projects. This enables the team to hire one or more NLeSC research engineers.

“Path-Finding” projects are intended to provide the opportunity to rapidly meet short-term scientific challenges, serve as a pilot for future research activities, address immediate technological goals or investigate the potential to initiate full projects.