poltextlab_admin

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/

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.

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

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.

On 2 October 2025, Miklós Sebők participated in a book launch and academic discussion at the ELTE Centre for Social Sciences, where sociologist and political scientist Andrea Szabó presented her new book, titled “Pattern Following and/or Independent Opinion – Trends in Political Interest in Hungary.”  As part of the event, Miklós Sebők emphasised that Hungarian political interest remains low by European comparison, despite recent signs of change after 2020. He highlighted that shifts in interest have historically been tied to regime changes and critical elections, and that variations are visible across generations and social groups. The presentation explored how political apathy can sometimes signal democratic satisfaction, while renewed civic engagement often emerges during moments of disillusionment. Further details of the event can be found here: https://index.hu/belfold/2025/10/03/politika-kozelet-politikai-erdeklodes-valasztas-rendszervaltas-szabo-andrea-bocskei-balazs-sebok-miklos-valuch-tibor/ Photo: Szollár Zsófi, Index, October 3, 2025