News

7 November 2025 – Miklós Sebők on AI in comparative politics at the Bryan D. Jones conference in Austin

On 7 November 2025, Miklós Sebők delivered a presentation at the University of Texas at Austin during the panel Building the Dataset, organised as part of the broader event “A Celebration of The Policy Agendas Project and Bryan Jones.” In his contribution, Sebők highlighted the AI-assisted methodological and conceptual innovations required to construct robust, longitudinal policy datasets. He discussed challenges in ensuring coding consistency, integrating heterogeneous political information, and adapting established frameworks to new digital and multilingual sources. Sebők underscored the unique Importance of the Policy Agendas codebook developed by Bryan D. Jones and Frank Baumgartner. His presentation showed examples of how the collaborative, cross-national data project strengthens the analytical foundations of the Policy Agendas Project and enables more precise comparative research on policy change.

6 November 2025 – Ádám Kerényi chairs panel at Network for European Studies Conference

Ádám Kerényi chaired a panel on Competitiveness and Economic Development at the “2nd Network for European Studies Conference”. The event took place on 6 November, and was hosted by National University of Public Service. The session featured presentations by the following speakers: Enikő Győri (Member of the European Parliament), Csaba Fási and Petra Szűcs (National University of Public Service), Gabriella Németh (University of Szeged), Krisztián Manzinger and Ákos Kántor (Károli Gáspár University of the Reformed Church in Hungary).

31 October 2025 – Models developed by poltextLAB were used in research on parliamentary conflict in Portugal

Models developed by poltextLAB were applied in new research on parliamentary conflict in Portugal, using a newly released dataset on legislative activity. The Portuguese Parliament (Assembleia da República) Roll-Call Votes Dataset (1980–2024) has just been uploaded to the Harvard Dataverse, covering all legislative proposals from the II Legislature (1980–1983) to the XV Legislature (2022–2024). From 1999 onwards, proposals are classified into 21 major policy categories based on the Comparative Agendas Project (CAP) framework, using CAP Babel Machine models. This version of the dataset was used in a recent article co-authored with Sofia Serra-Silva and Tiago Silva examining how the entry of the radical right into Parliament has contributed to escalating parliamentary conflict. The study is available here: https://www.frontiersin.org/journals/political-science/articles/10.3389/fpos.2025.1553921/fullDataset available here: https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/VJDEVKResearchers and practitioners can also access the models developed by poltextLAB on HuggingFace: https://huggingface.co/poltextlab The Babel Machine is available here: https://babel.poltextlab.com/

29 October 2025 – Miklós Sebők’s workshop on Generative AI at the University of Tampa

On 29 October 2025, Miklós Sebők held a workshop for the University of Tampa’s faculty and computer science students titled Generative AI for Research (with some computer science applications). The session explored how generative artificial intelligence tools, including large language models, can enhance academic research workflows across the social sciences and computer science. Dr Sebők demonstrated practical examples of AI-assisted data collection, text analysis, and literature synthesis, showing how these tools can accelerate empirical and theoretical investigations.

24 October 2025 – poltextLAB awarded Big Data Value Association Bronze i-Space label

On 24 October 2025, poltextLAB was awarded the Bronze i-Space label by the Big Data Value Association (BDVA). This quality label recognises excellence based on a set of key performance indicators (KPIs) evaluated across six pillars: infrastructure and data, services, sectoral projects, ecosystem and impact, sustainability, and federation. The assessment was conducted by a panel of independent experts. The Bronze i-Space label is valid for two years and highlights poltextLAB’s growing role in fostering data-driven innovation and research collaboration within Hungary and across Europe.

17 October 2025 – Models developed by poltextLAB were used in research on Portugal’s 2024 European Parliament elections

Models developed by poltextLAB were applied in new research on the 2024 European Parliament elections in Portugal. The article by Tiago Silva and Marina Costa Lobo, titled The 2024 European Parliament Elections in Portugal: Media, Results, and Vote Determinants in National and European Elections, was published in South European Society and Politics. The study examines how media coverage, voter behaviour and political determinants shaped the elections. The study is available here: https://doi.org/10.1080/13608746.2025.2553038Researchers and practitioners can also access the models developed by poltextLAB on HuggingFace: https://huggingface.co/poltextlab

3 October 2025 – The ParlText database V2 version is released

The V2 version of the ParlText database is released. The database is a comprehensive collection of legal and parliamentary texts, specifically focusing on Central-Eastern Europe (namely it includes the legislative speeches and laws of Czechia, Hungary, Poland, and Slovakia). It contains nearly 2.3 million text vectors and metadata covering the period from the early 1990s up to 2024. The dataset features essential information such as dates, text content, policy titles, and, for speeches, parliamentary agendas, and speaker names.

2 October 2025 – Nathalie Neptune’s presentation on Integrating Geospatial and Legislative Data at poltextLAB

On 2 October 2025, guest researcher Nathalie Neptune gave a workshop at poltextLAB on how satellite data can be combined with legal and policy information to study forest management and wildfire control in Hungary. She demonstrated how changes in forest laws — such as those governing harvesting rules, conservation, or emergency logging — can be linked to satellite indicators, including forest loss, burned area, and vegetation health. This approach helps reveal whether and when new policies have had visible effects on Hungary’s forests. The project employs advanced statistical methods, including interrupted time-series analysis, regression models, and Bayesian structural time-series (BSTS) models, as well as case studies. These methods test whether legislative changes correspond to measurable shifts in forest conditions or wildfire frequency, offering evidence to support more adaptive and data-driven forestry and fire management strategies. The Hungarian Academy of Sciences Distinguished Guest Scientists Fellowship Programme supports this research.