Mining Shifting Concepts Through Time (ShiCo)

Word vector text mining change and continuity in conceptual history

Image: View of Ancient Florence by Fabio Borbottoni. Emerging cities such as Florence gave people new opportunities to be a citizen of their city. Citizenship as a concept is difficult to define because it changes over space and time.

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. Currently the notion that concepts are stable unit-ideas that constitute the continuous foundation of changing historical debates, just as chemical elements can form different molecules, is being revaluated.

The scientific goal of this project is to develop a 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. 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.

Impressive progress has been made in tracing and mapping historical events and actors as well as past relations between actors and events. This project aims to go beyond these capabilities by establishing the structures of interpretation that emerge around these historical events, and the subsequent formation of collective meanings.

Digitized repositories of historical newspapers and magazines offer crucial empirical data to explore our historical heritage. Produced and controlled by social ‘gatekeepers’ such as journalists, editors and publishers, their information-rich content and audience-oriented nature ensure that they reflect and mediate public opinion in the societies that produce them.

This project aims to make historically embedded cultural concepts visible in a way that enables researchers to trace the specific historicity of cultural concepts and their changes and continuities in meaning.

Participating organisations

Netherlands eScience Center
Utrecht University
Social Sciences & Humanities
Social Sciences & Humanities

Impact

Output

  • 1.
    Published in 2016
  • 2.
    Author(s): Martinez-Ortiz, Carlos, Kenter, Tom, Wevers, Melvin, Huijnen, Pim, Verheul, Jaap, van Eijnatten, Joris
    Published in 2016

Team

Joris van Eijnatten
Joris van Eijnatten
Principal Investigator
Utrecht University
Jisk Attema
eScience Coordinator
Netherlands eScience Center

Related projects

H-GEAR

Historiographing the Era of the American Revolution

Updated 7 months ago
In progress

EviDENce

Ego Documents Events modelling – how individuals recall mass violence

Updated 20 months ago
Finished

TICCLAT

Text-induced corpus correction and lexical assessment tool

Updated 21 months ago
Finished

GlamMap

Visual analytics for the world’s library data

Updated 20 months ago
Finished

Deep learning OCR post-correction

Evaluation and post-correction of OCR of digitised historical newspapers

Updated 20 months ago
Finished

From Sentiment Mining to Mining Embodied Emotions

Emotional styles on the Dutch stage between 1600-1800

Updated 3 months ago
Finished

DiLiPaD

A new approach to the history of parliamentary communication and discourse

Updated 20 months ago
Finished

Related software

H-gear

H-

This tool analyzes the transmission of political ideas during the American Revolution. It enables users to track shifts in concepts in letter correspondence networks, using semi-supervised topic modeling and temporal social network modeling to reveal ideological shifts and identify key influencers.

Updated 2 months ago
2

ShiCo

SH

A visualization that shows how the meaning we attach to a given concept shifts over time.

Updated 29 months ago
2 1