By: Ana Rubio Denniss, cross-posted from http://engmaths.org/narrative-network-analysis-of-british-power-structures/
To say that our society is shaped by the actions of individuals and institutions may seem obvious, but how could one quantify the prevalence and importance of such actions on society? This is the question that a University of Bristol research collaboration between the Intelligent System Laboratory (Thomas Lansdall-Welfare, Saatviga Sudhahar and Nello Cristianini) and Department of History (James Thompson ) set out to answer in their recent work “The Actors of History: Narrative Network Analysis Reveals the Institutions of Power in British Society Between 1800-1950”.
This work looks specifically at the roles of key players in British society over a 150 year period from 1800-1950 and how these societal roles changed over this time. These players may be individuals such as the reigning King or Queen, or institutions such as the Church. The analysis was undertaken using narrative network analysis, turning digital information from 39.5 million local newspaper articles published in this time into a series of narrative networks. The complex social interactions were transformed into these visual networks by representing the different players of influence as network nodes, the actions of these influencers as links and the closely interacting sections of society built around them as their surrounding communities.
The results of this data-driven analysis of 28.6 billion words taken from 150 years’ worth of newspaper reporting involves 29 networks comprised of 156,738 nodes connected by 230,879 edges. The image below shows one narrative network in a ten year period from 1905-1915, with coloured coded nodes denoting the broad topics to which they belong.
Colour coded network topics
Another key element of the work was the detection of communities, which was performed by computing the frequency with which different key players performed interactions to or on each other. Once communities had been computed around the nodes, macro-communities were formed to show community structures which were persistent over the 150 year period across the majority of the 29 networks. The resulting macro-community for the most central 1000 players in shown below.
The findings of this project are interesting in themselves, giving insight into the power structures of British society and how these link together to influence public life. However the project itself has much wider implications in terms of the application of computational tools, particularly AI algorithms in this case, to Digital Humanities. Due to the numerous library digitalization projects taking place worldwide, this field is rapidly expanding and requires tools with which to deal with the large number of resources becoming digitally available. The meaningful representations produced in this paper demonstrate that many of these tools already exist in the spheres of AI, big data and data visualisation, and that collaboration with these fields has great potential to provide information and understanding of qualitative resources.