BMFTR SynDIKAT

Duration: May 2026 - April 2029

PIs: Prof. Thorsten Quandt (Universität Münster), Prof. Christian Grimme (Universität Münster, Wirtschaftsinformatik), Dr. Dennis Assenmacher (Gesis – Leibniz-Institut für Sozialwissenschaften), Prof. Johannes Breuer (Center for Advanced Internet Studies), Prof. Tobias Gostomzyk (TU Dortmund)

Team: Paula Jung, Malin Richter

Funding: Federal Ministry of Research, Technology and Space

Keywords: online communication, social media, disinformation, synthetic data, simulation, artificial intelligence

Abstract

In the context of social media disinformation research, this project addresses the challenges arising from restricted data access and the lack of standardized benchmarks for evaluating algorithms and data. Without a suitable basis for comparing developed approaches and methods for detecting and combating disinformation—including its spread and impact—the applicability of all developed procedures remains anecdotal and scientifically non-transparent. The SynDIKAT project aims to develop a framework that facilitates data exchange between researchers while simultaneously considering data protection and licensing agreements. Furthermore—as a key solution to the benchmarking problem—the project proposes generating synthetic social media data using LLMs and agent-based simulations to create realistic and diverse datasets. In this way, the project aims to lay the foundation for an initially national and later international "Data Sharing Community" to advance research in the field of disinformation and improve the robustness and transparency of scientific findings. In addition to the Online Communication LAB, project partners include the Institute of Information Systems (Prof. Christian Grimme) at the University of Münster, GESIS – Leibniz Institute for the Social Sciences (Dr. Dennis Assenmacher), the Center for Advanced Internet Studies (Prof. Johannes Breuer), and the Chair of Media Law at TU Dortmund (Prof. Tobias Gostomzyk).