Deep Networks as Associative Interfaces to Historical Research

Abstract

The most widely used software tools for network analysis have the explicit goal of creating patterns that visualize features of the underlying data that are regarded as representative for answering research questions or testing hypotheses. Their underlying algorithms often support quantitative analyses and visualization of large data sets. Up to now statistical methods are used to explain to which extent these visualizations are representative for the underlying data. This contribution is based on the assumption that full data integration, in particular in the humanities, is impossible for reasons of incompleteness, complexity, ambiguity and uncertainty in data. Therefore the focus should not be on data analytical and statistical methods of network representations alone. We need to include approaches that allow users to handle, inquire and interpret these incomplete and complex data. We do not need just networks as representations, but also networks as interactive interfaces. These interfaces must enable users to explore and to interact with their own selections of data that can combine data-driven and research question driven approaches. Based on experiences with a large scale project Circulation of Knowledge/ePistolarium and a small scale experiment Mapping Notes and Nodes: Exploring potential relationships in biographical data and cultural networks in the creative industry in Amsterdam and Rome in the Early Modern Period, problems of labelling automatically generated topics and their impact on network representations are discussed. We claim that the computer assisted and manual creation of multi-layered networks, in so-called deep networks holds a promise for future historical networks research.