With the Swiss News Viz Media Lab the project team proposes to create an infrastructure that aims to provide expert tools and methods from the analysis of textual data in the form of a publicly accessible platform for both research and teaching purposes.
The novelty of the infrastructure is to give researchers access to a combination of different features through an online platform including:
The infrastructure is supported by the UpLORD (Upgrading the linguistic ORD-ecosystem) project and also collaborates closely with LiRI (Linguistic Research Infrastructure) for the development of the necessary tools and pipelines. In particular, it will benefit from the expertise of the LCP@LiRI (Linguistic Corpus Platform) team as a service for the hosting of complex linguistic annotated data allowing refined search and quantitative analyses.
The infrastructure aims to develop collaborations related to the elaboration of expert content analysis tools, data integration, facilities for additional features, as well as research replicability and archiving. Furthermore, it also focuses on building robust practices in data curation and integration, as well as documenting and promoting best practices on open data and reproducibility goals in the context of teaching, research and publishing.
Project duration: 01.10.2023 – 30.09.2025
Contact person: Maud Reveilhac
Dr. Maud Reveilhac has a background in political science, social psychology and survey research. She has worked at FORS (Swiss Centre of Expertise in the Social Sciences). She is currently Post-doc (Research and Teaching Assistant) in the Department of Communication and Media Research at Zurich University. Integration and complementarity of various data sources for the study of public opinion, as well as the transferability and adaptability of computational (social) research methods are at the centre of her research. She has published numerous articles and book chapters on these topics. She is also involved in research for enhancing reproducibility and replicability of research methods and processes.
Prof. Gerold Schneider directs the NLP Group of LiRI (also known as Text Crunching Center), which offers services and coaching in the area of Text Mining, Content Analysis and Digital Humanities to Universities and private industry. He is also post-doc in the URPP Digital Religion(s), specializing on hate speech detection and content analysis. He has ample research experience in Text Mining for medical, historical, political, social and religious domains and is author of over 120 articles and extensive teaching material, including the course book «Statistics for Linguists» (Schneider and Lauber 2019) and online course material, for instance for the Australian Text Analytics Platform (ATAP/LADAL). His interdisciplinary research applies computational linguistics and AI methods, such as the detection of semantic topics, individual styles, detection of mood and sentiment, text classification by statistical and deep learning methods to many applications, ranging from historical linguistics to chatbots. His competence for the planned infrastructure comprises implementing relevant computational approaches and the systematic evaluation of existing tools.
Prof. Noah Bubenhofer is Professor of German Linguistics at the Department of German Studies at the University of Zurich and Co-Director of LiRI Linguistic Research Infrastructure. His research areas are in the field of language and society, as well as quantitative methods of text analysis and corpus linguistics. In various publications on discourses in society, he not only used corpus linguistic methods, but also developed new approaches to identify typical language use in richly annotated data. As co-director of LiRI, member of the swissuniversities Open Research Data sounding board, and PI of the ORD project UpLORD, he is also committed to promoting ORD infrastructure and practices in linguistics and neighboring disciplines at the national level.