Context and motivation Humanities researchers have long studied how information and influence circulate through cultural systems. Advances in network visualization tools support this work, allowing scholars to create graphical representations of complex discursive and cultural systems. While both proprietary and open-source network mapping software have made generating high-quality and even dynamic network visualizations relatively easy, key challenges remain for humanities researchers. Primary among these challenges is the humanistic focus on unstructured textual data (novels, archives, poems, biographies, etc.). Creative, historiographic, biographical, and similar artifacts are usually not easily transformed into the kinds of data structures necessary for network visualization. Additionally, even when objects of study can be somewhat easily rendered into visualization-ready data formats, these transformations can be very time intensive and/or require advanced computational skills. Thus, there is a significant need for the development of new methods that can support humanistic researchers who need to transform unstructured textual datasets into data structures that support useful and informative network visualization. The Transparency to Visibility (T2V) Project was initiated to pursue these goals. The T2V team used bioethics accountability statements to pilot and evaluate different methods for transforming and visualizing relational networks based on data in unstructured text. The resulting machine-learning-enhanced natural language processing (NLP) and metadata-assisted approaches offer promising potential pathways for contemporary digital humanities and future toolkit development. In what follows, we provide a brief summary of the current state of network visualization methods in the digital humanities (section 1); describe the exigencies for the current project (section 2); and detail our approach to data extraction for subsequent network visualization (section 3). 1.1 Humanities network modelling In recent years humanities journals have seen an explosion in network mapping methodologies applied to social media discourse, scholarly citation networks, and all manners of archival and textual materials. The recent enthusiasm comes in part from the fact that network modelling