Computational history and big data

Detail from Fra Mauro’s ‘mappa mundi’, ca. 1450. Biblioteca Nazionale Marciana, Venice.

ON 14-16 November 2017, JIAS hosted a seminar on ‘Understanding the pre-colonial world through computational history’.

It was aimed at strengthening southern African input into the Interactive Global Histories (1205-1533) Project based at Nanyang Technological University in Singapore, and led by Prof Andrea Nanetti of the School of Art, Design and Media at NTU.

Besides a lengthy presentation, Prof Nanetti presented the workshop with two publications which cast light on his project as well as the growing field of computational social science and humanities. Descriptions of and links to the publications appear below.

Maps as knowledge aggregators

Andrea Nanetti, Angelo Cattaneo, Siew Ann Cheon and Chin-Yew Lin, ‘Maps as Knowledge Aggregators: from Renaissance Italy Fra Mauro to Web Search Engines’, The Cartographic Journal, Vol. 52 No 2.

In this paper, the authors present Fra Mauro’s mappa mundi (map of the world) as a case study of how a mediaeval map can be understood as a knowledge aggregator, a knowledge engineering tool that allows its users to assemble information of different kinds from different sources, guided by what the user wants to do with the synthesized whole. The paper is as result of the research collaboration between Nanyang Technological University (Singapore) and Microsoft Research on ‘Augmenting Bing Search through Automatic Narratives in the Interative Global Histories’, started in 2014-2015 and based on Andrea Nanetti’s ongoing research project Engineering Historical Memory (EHM).

Download the paper here.

Computational history: from big data to big simulations

Andrea Nanetti and Siew Ann Cheong*, ‘Chapter 19, Computational History: from Big Data to Big Simulations’. In Shu-Heng Chen (Ed.), Big Data in Computational Social Science and Humanities, Springer  Series on Computational Social Sciences (forthcoming).

The chapter first provides an overview of how big data and its mathematical calculation enter into the historical discourse. Second, it presents a complex network and data-driven approach to mining historical sources. Third, it explains how this tool allows historians to deal with historical data issues, and take advantage of the automatic extraction of key narratives to formulate and test their hypotheses about the course of history in other actions or in additional data sets. Lastly, it describes the vision of how this narrative-driven analysis of historical big data can lead to the development of multi-scale agent-based models and simulations to generate ensembles of counterfactual histories that would deepen our understanding of why our actual history developed the way it did, and how to treasure these human experiences.

  • Siew Ann Cheong is an Associate Professor in the School of Physical and Mathematical Sciences at NTU.

Download the chapter here.

Share This