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/twin4dem-ethics-manager-interview-ensuring-responsible-research/ Wed, 18 Mar 2026 08:54:45 +0000 https://twin4dem.eu/?p=1226

In this video interview, the TWIN4DEM Ethics Manager discusses the role of ethics in the project and the importance of ensuring that research activities are carried out responsibly and transparently.

The conversation highlights how ethical considerations are integrated across the project, including research design, data handling, and stakeholder engagement. It also explains why maintaining high ethical standards is essential when addressing topics related to democracy, governance, and executive aggrandisement.

This interview is part of the TWIN4DEM video series, which presents key project roles, research themes, and the broader impact of the initiative.

In this first video interview of the TWIN4DEM series, the project coordinator presents the vision and objectives of the project. The discussion introduces the motivation behind TWIN4DEM and explains how the consortium aims to advance research on executive aggrandisement and democratic governance.

The interview outlines the project’s approach to strengthening scientific excellence through international collaboration, interdisciplinary research, and the use of advanced analytical methods. It also highlights the broader relevance of the project for understanding contemporary democratic challenges and supporting evidence-based policy discussions.

Through this video series, TWIN4DEM will share insights from project partners, researchers, and stakeholders involved in the initiative, offering perspectives on key research themes, activities, and expected outcomes.

Over the past months, the consortium consolidated the analytical foundation of the Digital Twin on executive aggrandisement, mapped key political and institutional actors across four case studies, and validated core assumptions through onsite focus groups. An initial integrated version of the Digital Twin architecture has also been developed, alongside the delivery of seven public project outputs.

The 2nd General Assembly and the first Advisory Board meeting provided strategic alignment and external feedback, further strengthening the project’s analytical framework and policy relevance.

With a new round of online focus groups scheduled for March 2026, the publication of the first Policy Brief forthcoming, and continued model development underway, TWIN4DEM is advancing steadily toward delivering tools that support democratic resilience.

Read the full Newsletter #2 for detailed updates and upcoming activities.

📩 Read the newsletter here: TWIN4DEM 2nd Newsletter

Dates and Times (Online):

• 25 March, Wednesday, 10:00–12:00 – Czechia
• 25 March, Wednesday, 14:00–16:00 – France
• 26 March, Friday, 10:00–12:00 – Netherlands
• 27 March, Friday, 10:00–12:00 – Hungary

About TWIN4DEM

TWIN4DEM is an EU-funded research initiative that develops digital twin and computational approaches to analyse risks of democratic erosion in Europe. The project combines social science, data science, and participatory methods to support evidence-based policymaking and democratic resilience.

Following the first round of focus groups, the project has further developed its theoretical and computational models. This new round aims to validate and refine these tools through direct interaction with stakeholders.

Who Can Participate?

We are looking for a diverse group of participants, including:

– Policymakers (local, national, and EU-level decision-makers)

– Civil society representatives (NGOs, advocacy groups, democracy watchdogs)

– Researchers and academics (social scientists, political analysts, data scientists, legal experts)

– Media professionals (journalists, fact-checkers, public communicators)

– IT and digital innovation specialists, including experts interested in digital twins

– Citizens and activists with an interest in democratic governance and digital policy

Focus Group Objectives

This round of focus groups will focus on:

• Presenting updates to the TWIN4DEM theoretical model
• Demonstrating how previous focus group input was integrated
• Presenting the current state of the toy model
• Testing the model through hands-on interaction
• Collecting targeted feedback for further development

Participants’ contributions will directly support the validation, usability, and policy relevance of the digital twin.

Format & Timeline 

– Location: Online

– Duration: 2 hours

– Language: English

Why Join? 

• Contribute to the refinement of an innovative digital twin for democracy
• Influence the practical development of project tools
• Exchange perspectives with researchers, policymakers, and practitioners
• Support evidence-based democratic governance

How to Apply? 

Interested participants can express their interest by filling out a short online form. Selected participants will be contacted via email.

Feel free to share this invitation with colleagues, peers, or other contacts whom you believe would bring valuable perspectives to the discussion. We welcome wider participation from individuals whose work or interests align with the themes of democratic resilience and digital governance.

For more information, visit Home – twin4dem.eu or contact us at info@twin4dem.eu & proskurina@democracy-international.org

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.

As part of this dedicated session showcasing research initiatives, Laura Dioșan (UBB) presented an overview of the TWIN4DEM project, outlining its core aims, innovative use of Computational Social Science and digital twin technologies, and its contribution to understanding democratic resilience and executive aggrandisement in Europe.

The topics covered in the presentation included the project’s motivation, methodological approach, anticipated outputs and the ways in which TWIN4DEM seeks to advance multidisciplinary research on democratic backsliding.

More about the conference’s Projects Panel and the full list of participating research projects can be found here: https://innocomp.eu/projects-panel/2025

Clara Egger and Raul Magni-Berton presented “TWIN4DEM: A Conceptual Framework for Strengthening Democratic Resilience through Digital Twins.”
Their talk introduced the TWIN4DEM framework, which models democratic systems as interconnected complex network systems (CNS). Each module within this model represents a core democratic function. At the heart of the framework are three key types of institutional agents:

• Executive actors (e.g., heads of state, ministers)

• Legislators

• Judicial actors (in constitutional or administrative courts)

These agents possess either initiative or veto powers, and their actions are influenced by both structural incentives,such as electoral systems, party structures, and socio-economic contexts, and individual preferences, including policy priorities and authoritarian orientations.

Csilla Zsigmond, representing the Hungarian TWIN4DEM team, delivered a presentation entitled “Parallel Institutions: The ‘Soft’ Mechanisms of Executive Aggrandizement — The Case of the Mathias Corvinus Collegium.”Her analysis drew on theoretical perspectives that view de-democratization not only as the dismantling of democratic institutions but also as the gradual transformation of formal and informal power structures that erode pluralism, accountability, and political contestation. The presentation explored how the emergence of parallel institutional systems can contribute to the expansion of executive power.

Both presentations were featured in the session “Autocratic Tendencies and Democratic Responses,” organized by Margit Feischmidt, Márton Gerő, and Dániel Mikecz. Notably, Márton Gerő is also a member of the Hungarian TWIN4DEM team.

The TWIN4DEM project is hosting a series of focus groups to explore policy scenarios relevant to our research model. These discussions will centre on two categories of scenarios:

1. Internal political structures: Simulating risks of executive aggrandizement emerging from within a country’s own institutions.
2. External shocks and factors: Exploring the impact of crises such as pandemics, terrorist attacks, economic collapse, or EU-level pushbacks.

Participants will discuss key questions, including:

• How plausible is the scenario in their national context?
• Which actors are most relevant (executive, judiciary, parliament, media, civil society)?
• How might these actors behave considering their preferences, incentives, and constraints?
• What outcomes are most likely: aggrandizement, prevention, or active resistance?
• Are there safeguards, counterweights, or early-warning signals?
• What role might external actors and shocks play in shaping events?

Focus Group Schedule

• 23 September, 11:00 – 16:00 – Lille
• 25 September, 11:00 – 15:30 – Rotterdam
  • Followed by an open panel discussion on democratic reforms (16:30 – 18:30).
• 9 October, 10:30 – 15:30 – Prague
• 14 October, 10:30 – 15:30 – Budapest

Who Will Participate?

The focus groups bring together individuals with direct insight into democratic governance and institutional dynamics. Participants include:

• Civil society representatives actively engaged in safeguarding democratic values.
• Media professionals who monitor and report on political developments.
• Policy makers involved in shaping or implementing democratic reforms.
• Selected academics, where their expertise aligns with the scenarios under discussion.

If you are interested to join us and fall under one of these categories, please reach out to proskurina(at)democracy-international.org

What should democracy in the Netherlands look like in 2050? More citizen assemblies? More referendums? Or something entirely new?

We invite you to an event at Erasmus University Rotterdam that brings together experts, students, and citizens to debate and reimagine the future of democracy. This interactive panel and open discussion is an opportunity to share ideas, learn from democratic innovators, and connect with others who care about strengthening democratic resilience.

Why join?

• Discover democratic innovations and their impact in the Netherlands and beyond

• Contribute to a lively and interactive discussion

• Meet leading experts, activists, and students passionate about democracy

• Enjoy a free reception afterwards — network and exchange ideas

Confirmed panelists include:

• Eva van Schendelen (Ombudsman Rotterdam Rijnmond)

• Joep van Lit (Radboud University Nijmegen)

• Niesco Dubbelboer (Meer Democratie; former Member of Parliament)

• Lot Mertens (City Whisperer & Cheerleader of Local Democracy, Rotterdam)

Event details
Date: Thursday 25 September 2025
Location: Erasmus University Rotterdam, Sanders 0.04
Time: 16:45 – 18:00 (reception until 19:00)

Participation is free, but seats are limited. Make sure to register here.