Collecting Political Texts for the Detection of Executive Aggrandisement

The first step towards the goal of identifying executive aggrandisement and analysing politicians’ stance and reactions is the collection of relevant data. In TWIN4DEM, multiple textual sources are being integrated, including legislative texts, parliamentary debates and politicians’ social media posts. Although several initiatives aim at collecting and making available the above data, both through official channels such as Data.gouv.fr and based on researchers’ and activists’ initiatives such as the ParlaClarin project, the current infrastructure does not provide this comprehensive data ecosystem. Therefore, all partners involved in Work Package 3 are dealing with the challenges of finding, retrieving, processing and storing the data needed for the task. Among the most pressing issues there is the variability of data formats not only across countries but also across time. For example, parliamentary data may be available in a specific format only for some legislatures, while in TWIN4DEM we plan to cover the time period between 2010 and 2024, and we need to have a balanced set of data for the whole time span. Likewise, all political parties and positions should be equally represented in the data. 

Paradoxically, two additional challenges are data scarcity and data overflow. For example, while Twitter/X has been a popular communication channel used by politicians across Europe, this is not the case in Hungary, for which we will have to implement a different strategy to retrieve MPs’ public statements. On the other hand, sometimes the available data are just too much to be meaningfully processed to identify examples of aggrandisement. For instance, the number of regulative or administrative acts issued by ministers, prefects or mayors for the French use case is 245,500 documents, and this accounts only for a portion of all legislative data we will process in TWIN4DEM for France. In this case, we therefore need to narrow down the scope of our analysis by identifying a subcorpus with documents that in terms of topics, structure and linguistic expressions are likely to signal aggrandisement. This selection is driven by the domain experts in our consortium and requires a different strategy for each use case. By combining political scientists’ knowledge and a plurality of NLP techniques, we aim at describing and unveiling the “language of aggrandizement” in statutory documents. 

What comes next:

Despite current efforts, the output concerning WP3 data will provide a unique resource to the scientific community, data scientists, journalists, political organisations, activists, and more generally to all citizens interested in monitoring political activity. Indeed, while there have been initiatives to interlink metadata concerning politicians’ profiles, their activity in Parliament and biographical information, in TWIN4DEM we will make available a much richer database where politicians’ statements on social media will be aligned with their speeches in parliament, voting behaviour and much more. This will open new research directions to investigate the gap between politicians’ online behaviour and their statements in Parliament, their attitude with respect to their party orientation, their distance from other MPs. Novel NLP approaches will be enabled by this textual resource to detect executive aggrandisement, offer new perspectives on political opinions and make cross-country comparisons.

]]> https://twin4dem.eu/building-the-foundations-of-the-twin4dem-digital-twin/ Tue, 16 Dec 2025 18:25:05 +0000 https://twin4dem.eu/?p=1135 As we conclude the first year of TWIN4DEM, the project teams have made significant progress in laying the conceptual and technical foundations for the Digital Twin. This innovative model will allow us to simulate threats to democratic resilience and explore effective policy responses. In this first project update, we highlight the key developments in our conceptual and modelling work.

Understanding How Executive Power Expands

A central strand of work during the past months has focused on clarifying how executive power expands within democratic systems and how this process can be meaningfully modelled. This effort provides the analytical backbone of the Digital Twin, ensuring that political dynamics are captured in a way that reflects real-world complexity.

Key achievements include the development of a shared definition of executive aggrandisement, understood as situations in which governments expand their authority into areas traditionally reserved for other actors, thereby disrupting established checks and balances.

In parallel, the main political and institutional actors have been systematically mapped across the four case studies. These include governments, parliaments, courts, and other relevant players whose interactions form the core of the initial Digital Twin model.

Significant progress has also been made in identifying what drives actor behaviour. Structural conditions such as electoral systems, crisis situations, and institutional constraints have been organised alongside individual-level factors including career incentives, ideological orientations, and attitudes towards risk. Together, these elements help explain why actors respond differently to similar political pressures.

Country-specific expertise has been integrated through focus group discussions in each case study. These exchanges with local experts have tested whether the emerging model reflects political realities on the ground and have highlighted where adjustments are needed to capture national specificities. This step is essential to ensure that the transition from political theory to computational modelling remains empirically grounded.

Building the Digital Twin

Alongside the conceptual work, substantial advances have been made on the technical side of the Digital Twin. The overall architecture and module structure have been designed, translating analytical insights into a functioning computational framework.

Key developments include the completion of the conceptual design of the Digital Twin modules, the technical specification of the model structure and deployment options, and the implementation of an initial integrated version of the model. Early work has also focused on enabling dynamic interactions between political actors and influencing groups, allowing the model to simulate evolving political environments.

Preparations are underway to link the current model to real-world data, including the development of a data contract prototype that defines data sources, formats, and exchange protocols. This step is crucial for future validation and scenario simulations. Together, these elements represent the core building blocks required for the next phases of the project.

What comes next:

The next stage of work will deepen the country-sensitive nature of the model. Political systems in each case study will be described in greater detail, with particular attention to how executive, legislative, and judicial actors interact in practice. This includes identifying when formal distinctions between legislative and executive actions are politically meaningful and when they are blurred.

Building on this foundation, typical patterns of behaviour will be classified and connected to available empirical data on institutions, elections, crises, and other contextual factors. These inputs will be translated into a simple utility framework for each actor type, formalising how incentives and constraints shape expected choices. This step will enable a shift from a general conceptual model to consistent, country-specific representations of decision-making within the Digital Twin.

Towards a Stable and Scalable Model

Further technical milestones are planned in the coming period. These include the preliminary application of the Digital Twin using real-world data from one of the studied countries, the release of a model version based on a stable and robust technological stack, and the design of a sustainable software architecture that supports modularity, interoperability, and future development.

Rigorous internal validation will accompany these steps to ensure that the model performs as intended and meets defined technical and analytical specifications before broader use. Together, these advances will prepare the Digital Twin for more advanced simulations and policy-relevant analyses in the later stages of the project.