News

This year’s call for proposals for the MTA’s Momentum Programme received 108 valid proposals, 27 in the humanities and social sciences, 40 in the life sciences and 41 in the mathematical and natural sciences. Based on the peer review, the recommendations of the Momentum Jury and the Momentum Committee, the President of the Academy decided on 31 May 2023 on the ranking of excellence and the amounts of funding to be awarded to the research teams to be supported. As a result, a new Lendület research group will be established at the Centre for Social Sciences (CSS), Budapest, led by Miklós Sebők. The five-year project, funded with over EUR 560 000, is entitled: “The changing global relations of the Visegrad countries in times of war – An artificial intelligence-assisted comparative analysis”. Dr Sebők is a research professor at the Institute of Political Science CSS, and the National Laboratory for Artificial Intelligence at CSS, as well as the principal investigator of poltextLAB (poltextlab.com), a research lab dedicated to text mining and artificial intelligence applications in the social sciences. The project will extend the lab’s machine learning-based analysis of public policy agendas to the history and current data sources of the Visegrad countries after 1990, with the help of the lab’s collaborators and national and international partners.

The European Consurtium for Political Research (ECPR) has recognized the following poltextLAB publication with an honourable mention: Miklós Sebők, Bálint György Kubik, Csaba Molnár, István Péter Járay, Anna Székely:Measuring legislative stability: a new approach with data from Hungary (You can read the journal article here.) The Jacqui Briggs EPS Prize is awarded for an article that makes a substantial contribution to the field of political science, especially articles that contribute to the understanding of new and innovative trends in political science or to innovative approaches to teaching and learning in the profession.

On 23rd May, 2023 the “Text Mining and Artificial Intelligence Training Program” was successfully held by Orsolya Ring, Ákos Máté and Péter Gelányi with 11 beginner level and 5 advanced level participants. The course introduced participants to basic text mining tasks and their applications in social sciences. They were given an overview of the differences between information retrieval and information extraction, as well as the concept of bag of words and sentiment analysis.

Members of poltextLAB attended a conference of the COMPTEXT international text mining network in Glasgow from 12 to 13 May. At the COMPTEXT conference, poltextLAB’s research was presented at the following presentations: Miklós Sebők – Amnon Cavari – Ákos Máté:Assessing the Policy Agenda of U.S. Presidential Speeches – A Sentence-Level Deep Learning Approach Ákos Máté – Miklós Sebők – Ádám Feldmann:The last frontier for automated classification in comparative politics? Using multilanguage large language models Péter Gelányi:Tipping the scales: A text mining analysis concerning the effects of government influence on online media in Hungary The conference program is available here.

The journal article by Miklós Sebők, Rebeka Kiss and István Járay has been published in the Journal of Knowledge Economy on May 8, 2023, entitled Introducing HUNCOURT: A New Open Legal Database Covering the Decisions of the Hungarian Constitutional Court for Between 1990 and 2021. The article is available here: https://doi.org/10.1007/s13132-023-01395-6 The PDF version can be found here: https://link.springer.com/content/pdf/10.1007/s13132-023-01395-6.pdf

The Visegrad Fund approved the funding of the grant proposal ‘Identifying News Slant in Crisis Communication Using Artificial Intelligence’ of the Centre for Social Sciences. Orsolya Ring, a research fellow at the Institute of Political Science and senior researcher at poltextLAB, lead the one-and-a-half-year research programme. The research, with partners from the Czech Republic, Poland and Slovakia, will investigate the bias associated with different crises in online media using artificial intelligence.

The poltextLAB team’s submission for the SLICES-SC consortium’s “2nd SLICES-SC Open Call” has been successfully accepted. The SLICES-SC project builds a community of researchers around SLICES-RI, which offers the necessary solutions to create and manage efficiently IT-related experiments. As per the successful proposal, poltextLAB will be granted access to the imec research group iLab.t‘s GPULab infrastructure starting from April 2023. The GPULab is a testbed with 125+ GPUs with over 570.000+ cuda cores and 1.8TB+ GPU RAM for AI research and every research that needs GPUs. The poltextLAB team will exploit imec’s infrastructure to carry out a finetuning experiment of the large language models used in the CAP BABEL MACHINE project.

Nathalie Neptune – researcher at Institut de Recherche en Informatique de Toulouse (IRIT) – will be taking part of the Visiting Professorship program in April 2023. Neptune will be working in poltextLAB on the hyperparameter tuning of monolingual and bilingual Longformer models as part of the CAP BABEL MACHINE project.

On January 26-27, 2023, the Institute of Informatics of the University of Szeged hosted the Hungarian Conference on Computational Linguistics for the nineteenth time, which presented research and results in the field of language technology. At the conference, researchers from poltextLAB gave a presentation entitled “HunEmPoli: a Hungarian language, extensively annotated emotion corpus” in the Corpus and Databases section. The conference website is available here: https://rgai.inf.u-szeged.hu/mszny2023 The conference proceedings are available here: https://rgai.inf.u-szeged.hu/file/430

Orsolya Ring and István Üveges created the emotion corpus which is available on the project’s GitHub page. “The (manually annotated) HunEmPoli corpus was built using pre-agenda speeches from the 2014-2018 parliamentary term, and was created within the framework of the Hungarian Comparative Agendas Project (CAP) of the Institute of Political Science of the Centre for Social Science Research, and is freely accessible for research purposes upon registration. In the course of our research, we created an inductive emotion category system, the categories of which can later be mapped to Plutchik’s emotion category system, which distinguishes eight classes and is also convertible to the positive-negative categories used in sentiment analysis. This extended system was necessary because, in our previous experience, sentences in political texts could not be classified into one of the most commonly used Plutchik’s category systems for emotion analysis, or only with very low annotator agreement, whereas the extended system allowed the corpus to be annotated with high inter-annotator agreement. In the final annotation guide, a total of 12 so-called emotion topics (ET) were defined, each of which was accompanied by at least three call words or phrases to facilitate the annotators’ work.” You can continue on this link.