News

On October 7, 2025, poltextLAB organised a full-day Generative Artificial Intelligence (GenAI) Analysis training. The course led by Miklós Sebők and Rebeka Kiss, aimed to provide a comprehensive overview of the application of generative artificial intelligence in different areas, with a particular focus on methodological foundations, ethical considerations, and the integration of GenAI into specific processes. The full-day training was structured into three main blocks: the first introduced the fundamentals of generative AI, including how large language models work, their limitations, and related ethical and legal issues. The second focused on prompt engineering, model selection, and comparing costs and performance. The final section explored practical applications — from data analysis and visualisation to literature review and research workflows — highlighting both opportunities and responsible use.

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

Orsolya Ring gave a presentation at the 3rd MEDem (Monitoring Electoral Democracy in the EU) Conference, held on 29–30 September 2025 in Cologne. Her talk, titled “Integrating Frameworks, Databases, and AI in Comparative Research,” introduced a novel approach to combining established coding frameworks, multilingual databases, and AI-based analysis tools to advance cross-national research in political and media studies. The presentation illustrated how the Comparative Agendas Project (CAP) can be connected with AI-assisted tools such as the Babel Machine, a no-code solution enabling automatic classification of texts across more than 100 languages. This integration supports greater comparability, scalability, and replicability in media and policy research. Find more details about the conference here: https://www.medem.eu/from-data-to-impact-medem-conference-2025/ 

From 25 to 27 September 2025, the Látkép (Panorama) – Art History Festival was held for the second time in Budapest, this year focusing on digitalisation and technological innovation. As part of the festival, on 27 September, poltextLAB organised a Generative AI workshop titled “The Future of Visual Arts: AI-based Digital Solutions”. The workshop demonstrated how generative artificial intelligence (GenAI) – such as Stable Diffusion, Midjourney, and similar models – is transforming both research and creative processes in the visual arts. Participants were introduced to concrete examples of the scientific use of these tools, including image classification and linking to metadata, object recognition in paintings with the help of GenAI, and producing iconographic descriptions based on images. The session also emphasised discussion of scientific integrity, transparency of data sources, and the ethical issues that arise from the application of generative AI.

On 25 September 2025, the Centre for Socio-Political Data (CSDP) hosted a discussion titled Café de la donnée on the topic of AI and social science metadata. Short presentations were delivered by researchers from several institutions – including Inserm, INSEE, and poltextLAB. Representing poltextLAB, Miklós Sebők demonstrated how artificial intelligence can support the better organisation and easier accessibility of research data. The event was interactive: participants not only listened to presentations but also engaged in a joint discussion. The following day, 26 September 2025, the first meeting of the FAIRwDDI scientific and technical board took place at Sciences Po in Paris. Participants discussed how to align the description of research data (also known as metadata) with the international FAIR principles. These principles ensure that data can be easily found, accessed, linked, and reused. The meeting aimed to define common directions for the future management of social science data.Both events highlighted that artificial intelligence and well-structured metadata play a key role in making social science research more efficient, transparent, and accessible in the future.

On 24 September 2025, Miklós Sebők, Research Professor at the ELTE Centre for Social Sciences, delivered a workshop titled Using advanced AI solutions for text-based social and economic research at the University of Namur. The event introduced participants to conceptual foundations of generative AI, the current state of large language models (LLMs), and their application in content classification, literature search, and applied regressions. Sebők compared API-based and local uses of LLMs and discussed the role of AI agents in data collection. The workshop was designed as a hands-on session accessible to all levels, from beginners to advanced researchers.

On 23 September 2025, Miklós Sebők delivered a lecture at the University of Namur as part of the “Methods Seminar” series. His talk, titled Solving classification problems for social and economic research with the Babel Machine, introduced how natural language processing and large language models can be applied to the analysis of social science and economic data. He also outlined the potential of AI-driven multilingual tools for addressing classification challenges in empirical research, with examples from ongoing projects. The presentation illustrated how machine learning methods expand opportunities for computational social science by enabling richer and more scalable text analysis.

On October 7, 2025, poltextLAB will hold a full-day training on Generative Artificial Intelligence (GenAI) at Corvinus University of Budapest. The program is designed for researchers and professionals who work with documents, writing, or data and want to understand how generative AI can be applied in their everyday work. The training will provide an introduction to the fundamentals of generative models, hands-on practice in prompt engineering and model selection, and practical examples of research applications. It will also address key ethical and legal issues, including data protection, intellectual property, and proper citation practices. More details and registration: https://bit.ly/4n3Du7E