Our research primarily focuses on novel models, techniques and tools in support of diverse NLP tasks, information extraction, data/text mining, machine learning/deep learning, and network analysis. In terms of data, we are particularly interested in text data, e.g., news articles, social media data, or Wikipedia documents,  as well as spatial, temporal, and spatio-temporal data, the latter either represented explicitly, e.g., in the form of time series, or extracted from text documents through information extraction techniques. Our research also has a strong interdisciplinary component, spanning the natural sciences, medicine, the humanities and the social sciences.

  • Bildung: Zusammen mit Prof. apl. Nicole Marme und Dr. Jens-Peter Knemeyer arbeiten wir an neuen Bildungsformaten für die Informatik in der Schule. Hierzu gehören die Zukunfts-Orientierungs-Akademie für Schülerinnen der Oberstufe (ZoRA) und im Kontext KI in der Lehramtsausbildung in MINT-Fächer im Programm KI-Campus eine Lernplattform für Künstliche Intelligenz.

  • Computational Social Sciences: In October 2020, the project "Exploration of Political Information Networks" (EpiNetz) started. The project is supported by the Klaus Tschira Stiftung GmbH  and is a collaboration with the Political Sciences Group of Prof. Dr. Wolf Schünemann at the University of Hildesheim. Based on large collections of news data related to politics and society (Twitter, News Outlets, documents of the EU and German Bundestag, and many other), a wide variety of methods and tools for the analysis and exploration of text data is developed and provided to the public, ranging from pupils to researchers.

  • Consumer Protection: Together with the group of Prof. Mario Martini, Chair of Public Administration, Public Law, Administrative Law and European Law at the University Speyer, in the project "Dark Pattern Detection (DaPDe)", we investigate how websites and apps  make you do things that you didn't mean to, like buying or signing up for something. The project includes several legal aspects as well as technology development for automatically detecting such patterns on websites.

  • Data Science in Health: Prof. Dr. Michael Gertz is co-speaker of the Helmholtz Information and Data Science School for Health (HIDSS4Health), with a focus on personalized medicine, integration, analysis and exploration of heterogeneous, time-evolving clinical data.

  • Medicine: information extraction from clinical admission notes, analysis and exploration of patient health monitoring data, see also the projects Informatics4Life and SCIDATOS (involved until Feb 2019)

  • Law: extraction of implicit information networks from norms and law texts, reaching into the area of Computational Law; see also our Doctoral Research Training Group “Digitales Recht” in collaboration with the Law School at Heidelberg University.

  • Political Sciences: information extraction from news articles and social media such as Facebook, dynamic information networks to explore topics, persons, and organizations over time; see also the project “Wahlkampf in (a)sozialen Netzwerken"

  • Economics: construction, modeling and analysis of finance networks; information extraction from finance data, embeddings of time series data into network structures; see also our Marsilius Project together with Prof. Christian Conrad.
  • Physics: extraction of networks from observation data to analyze and explore (evolving) structures and patterns in the data; Physics in fact is an important driver of many eras in Networks Science.

  • History/Theology: management and analysis of historic correspondence data, extraction and exploration of diverse information networks derived from historic correspondences/letters, see also the project "Theologenbriefwechsel im Südwesten des Reichs in der Frühen Neuzeit".

Beyond these academic collaborations and projects, the research group also works together with industry, for example, SAP (especially the SAP HANA Spatial Group).