Use of AI for early detection of criminal offences

KISTRA is a CATALPA project.

Project goals and research questions

Police crime statistics show a significant increase in politically motivated Internet-related crimes in recent years. Investigating authorities need tools that are tailored to their needs, enable pre-filtering and support them in criminal prosecution. KISTRA explores the possibilities of using Artificial Intelligence to detect, prevent and prosecute crimes. The subproject led by CATALPA research professor Torsten Zesch is specifically concerned with the question of how the criminal liability of hate speech in social media can be modeled computer linguistically.

  • Prof. Dr.-Ing. Torsten Zesch

  • Bmbf LogoFoto: BMBF

    The project is funded by the German Federal Ministry of Education and Research (BMBF) within the framework of the funding line

    Funding announcement:

    Funding reference: 13N15344

    • Zentrale Stelle für Informationstechnik im Sicherheitsbereich (ZITiS), München
    • Ruhr-Universität Bochum
    • Bundeskriminalamt, Wiesbaden
    • Ludwig-Maximilians-Universität München
    • Rheinisch-Westfälische Technische Hochschule Aachen
    • Technische Universität Berlin
    • Technische Universität Darmstadt
    • Universität Duisburg-Essen, Duisburg
    • Munich Innovation Labs GmbH, München
  • Piush Aggarwal

  • July 2020 - December 2023

  • 2022


    • Ludwig, F., Dolos, K., Zesch, T., & Hobley, E. (2022). Improving generalization of hate speech detection systems to novel target groups via domain adaptation. Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH), 29–39.
    • Zufall, F., Hamacher, M., Kloppenborg, K., & Zesch, T. (2022). A legal approach to hate speech – operationalizing the EU’s legal framework against the expression of hatred as an NLP task. Proceedings of the Natural Legal Language Processing Workshop 2022, 53–64.