'Text as data':
The project “Political and Legal Text Mining and Artificial Intelligence Laboratory (poltextLAB)” provides an interdisciplinary platform for researchers of political, legal, and administrative fields who use quantitative text analysis as their core method.
Quantitative text analysis and text mining:
- dictionary-based algorithms
- supervised and unsupervised learning
- multimedia mining
- data storage and retrieval
- big data clustering techniques,
- tools for data visualization
- empowering academia
- fostering collaborative research
- establishing best practices to overcome methodological issues resulting from language-specific limitations or unstructured data sources
- making text mining methods part of research designs in political science, legal studies, and public administration
Miklós SEBŐK is a Senior Research Fellow at the Centre of Social Sciences in Budapest. He earned an M.A. degree in politics at the University of Virginia and an M.A. degree in economics at the Corvinus University of Budapest. He received his Ph.D. in Political Science from ELTE University of Budapest. He currently serves as the director of the Institute for Political Science at the Centre for Social Sciences in Budapest. Miklós Sebők is also the research director of the Hungarian Comparative Agendas Project and the research co-director of the Artificial Intelligence National Lab at CSS, Budapest. His research interests include political economy, public policy and the application of text mining and machine learning methods in these fields.
Orsolya RING received her Ph.D. in History from ELTE University of Budapest. She is working in poltextLAB Project on creation and classification of large-scale newspaper corpora and elaboration of a domain-specific method for Hungarian sentiment analysis applying various machine learning methods. She is also working on the building of large-scale historical text corpora and its analysis by NLP methods in the Research Group Computational Social Science (CSS-RECENS).
Akos MATE studied political economy (PhD, Central European University) and network science (Advanced Certificate, Central European University). His main research interest is the application of quantitative text analysis and other big data methods in the political economy field. In the poltextLAB project he is taking part relating to cloud infrastructure and processing large-scale text corpora
György Márk Kis
György Márk KIS studied political science (BA, ELTE), public policy (MA, Central European University), and statistics (MSc, ELTE). During the past few years he worked at NGOs, in market research, and also served as an external contributor to the Hungarian CAP project. His primary fields are network science, the statistical modelling of complex systems and their application to the study of policy dynamics.
Csaba MOLNÁR studied political science (BA, MA Corvinus University of Budapest, BA, Nottingham Trent University). He is currently a PhD student of the Doctoral School of Political Science of the Corvinus University of Budapest. In poltextLAB, he is responsible for NLP-related and database building tasks. His main research fields are right-wing radicalism and legislative studies. He also participates in the Hungarian Comparative Agendas Project where he works on legislative database development.
Adam Kovacs is a cultural anthropologist (BA, University of Miskolc) and an expert in ethnic and minority policy (MA, ELTE). He is a PhD candidate at the ELTE Faculty of Social Sciences. Previously, he worked in public administration and at NGOs. In poltextLAB he is dealing with writing proposals.
Anna SZÉKELY studied sociology (BA, CUB), cultural anthropology (BA, BBTE), currently studies Regional and Environmental Economics (MA, CUB), and is a member of Széchenyi István College for Advanced Studies. Her main interests are unsupervised learning methods in text mining and the possible improvement of pre-processing methods (stemming and lemmatization) applied in quantitative text analysis for Hungarian texts. Related to poltextLAB she coordinates the OPTED project and adopts education content of poltextLAB to various platforms, such as Medium, GitHub, YouTube.
Ágnes Dinnyés studied international studies (BA) at Eötvös Loránd University. She was an intern in the poltextLAB project for two semesters, where she performed sentiment analysis-related tasks. She is currently working in the OPTED project, where she performs research and administrative tasks.
Péter Gelányi studied political science (BA, ELTE), currently studies political science (MA, ELTE). His primary research topic is the application of unsupervised classification methods to political research subjects.
Csenge Guba graduated with a master’s degree in theoretical linguistics from the University of Szeged, and she is currently a student at the University’s Doctoral School of Linguistics. Her research topic is sentiment and emotion analysis on Hungarian texts. She is working as a research assistant on the “Elaboration of a domain-specific method for Hungarian sentiment analysis” project of poltextLAB.
István Péter Járay
István Péter Járay studied Applied Economics (BA) at Eötös Loránd University. He wrote his BA Thesis about the attrition of young researchers in Hungary with the supervision of János Köllő through an agency contract with MTA KRTK KTI. His first published co- authorship was with the seniorship of Balázs Lengyel in researching future academic success of PhD students based on their co-authorship network. He is currently member of István Széchenyi College for Advanced studies where he accumulated relevant skills to his work at PoltextLab such as Data Science-oriented programming in Python, academic writing and understanding research design.
Eszter Fanni Lancsár
Eszter Fanni Lancsár studied political science (BA), which she currently continues on an MA level at the Corvinus University of Budapest. She participated in the Hungarian Comparative Agendas Project where she worked on the legislative database development. In the poltextLAB project, she performs research and administrative tasks in the OPTED project.
István Üveges is a 4th year Ph.D. student at University of Szeged, Doctoral School in Linguistics, and a 3rd year Computer Science student also at University of Szeged. He is participating in TK MILAB, “Elaboration of a domain-specific method for Hungarian sentiment analysis” project at Centre for Social Sciences, Artificial Intelligence National Laboratory. His main interests are legalese (legal language), Plain Language Movement, Natural Language Processing, Artificial Intelligence and Machine Learning.