Use Case
PolyGraphs data animation from Northeastern's Center for Design; PolyGraphs, Northeastern University, CC-BY-NC-ND 4.0
Polygraphs’ methods and approaches have been expanded by the addition of custom data ‘processors’, code modules which essentially extend the range of analyses that can be performed with simulation data to broaden research on epistemic attitudes across domains.
Research Context
PolyGraphs is an ongoing computational humanities project in social epistemology. It uses computational methods to simulate the effects of mis- and disinformation on communities of rational agents, exploring the relative roles of social network structures, informational environments, and information processing strategies in influencing epistemic attitudes.
With financial support from the Royal Society and others under an APEX Award from 2021-2023, a scalable framework for philosophical simulations was developed and is available on GitHub (https://github.com/alexandroskoliousis/polygraphs.git). This enables researchers to perform experiments – effectively, batches of simulations of the (practical and theoretical) behaviour of these communities under various configurations, i.e. sets of values for the independent variables. Running these simulations generates synthetic data, which need to be analysed and interpreted.
As a DISKAH Fellow and through engagement with DRI, Prof Ball’s research on the PolyGraphs simulation framework focuses on the potential to be further generalized – notably to new models of rational agents, of the communities they belong to, and of the informational environments in which they operate; as well as to new empirical/real-world and not merely artificially generated data sets, e.g. to model climate mis- and disinformation, or decision-making in business contexts.
Skills and Support
DISKAH has enabled Prof Ball to enhance digital skills capacity to effectively work with PolyGraphs. This includes more efficient coding in Python and software refinement, improved data management practices (e.g. through Globus), better understanding of data analysis and visualisation libraries in Python and improved familiarity with computational environments, including the ability to overcome challenges, such as library dependency issues. Moreover, access to RSE support has enabled work on PolyGraphs’ containerisation as part of efforts towards installation across systems and documentation development.
Methodology
Given the nature of PolyGraphs, which runs large scale simulations generating synthetic data for analysis and interpretation, the project was already computationally intensive and HPC dependent. The use of PolyGraphs’ by researchers requires easy deployment in HPC systems with different configurations supported by appropriate documentation. Users run batches of simulations in HPC under various configurations to generate synthetic data. This includes the use of job arrays by the PolyGraphs’ team to run simulation sub-batches (25 simulations instead of 100) in parallel and perform further experiments with new values for key variables, finding new correlations influencing epistemic attitudes.
Good data management practices and data moving across systems is a key challenge in this process as the resulting data is further processed using the analysis module from PolyGraphs.
Such analysis strengthens the research potential to model mis- and disinformation, as well as decision-making in different contexts, allowing users to explore epistemic attitudes. PolyGraphs’ methods have been expanded to extend the range of analyses that can be performed with simulation data. Future work for the project includes extending PolyGraphs to new models and empirical or real-world datasets to model mis- and disinformation or decision-making in other contexts.
Research Impact
The research has facilitated and strengthened networks with industry partners, as well as civil society and policy makers. Such engagement has contributed to establishing new partnerships focusing on investigating the role of AI in intellectual processes and knowledge production. Moreover, evidence from the research has informed policy discussions between governmental bodies and advocacy organisations on disinformation and democracy. Ongoing efforts are currently exploring further pathways to influence policy and practice.
Project Outputs
Github repository for PolyGraphs: https://github.com/alexandroskoliousis/polygraphs
Blogpost: Ball, B. (2026). The Number of Reliable Informants Affects Efficiency of Inquiry in PolyGraphs Simulations, Computational Philosopher, March 2026.
Scholarly publications:
Ball, B. et. Al. Introducing PolyGraphs, part 1: Running Philosophical Simulations. (under review)
Ball, B. et. Al. Introducing PolyGraphs, part 2: Analyzing Synthetic Data. (under review)
Ball, B. Structure Meets Strategy in the Misinformation Age. (in preparation)