HybriD – Real-time detection and identification of hybrid disinformation campaigns in online media

Duration: October 2021 to September 2024

Conductor: Prof. Dr.-Ing. Christian Grimme (University Münster), Prof. Dr. Thorsten Quandt (University Münster), Prof. Dr. Christian Stöcker (HAW Hamburg)

Assistance: Svenja Boberg, M.A., M. Saïd H. Unger, M.A., Johanna Klapproth, M.A.

Institutions: Department of Information Systems (University Münster), Department of Communication (University Münster), Department of Information (HAW Hamburg), Complexium GmbH (Berlin)

Funding: Federal Ministry of Education and Research (BMBF)

Keywords: Disinformation, disinformation campaigns, fake news, social bots, net-publics, methods of communication science, computational methods

Link: https://hybrid.social/

Abstract

Disinformation has been the focus of research and public debate for some time. Incidents such as the manipulation of journalistic forums during the early days of the Ukraine conflict, the suspected influence of disinformation in the Brexit referendum, or the use of automated communication in the 2016 U.S. election have drawn public and political attention to the issue. This leads to the central question: How do disinformation campaigns behind all these incidents work?
Since the above-mentioned events, research has increasingly focused on automated communication, fake news and hate speech, and how to detect them. Many citizens face these phenomena on a daily basis. The intensive study of disinformation strategies has revealed that, in addition to automated communication, there are sometimes covert aspects and actors that make a disinformation campaign powerful in the first place. In order to identify, understand, and combat the sometimes concerted disinformation campaigns, it is also necessary to take into account human actors, content, and timing.

Methods

The goal of the joint project "Real-Time Detection and Identification of Hybrid Disinformation Campaigns in Online Media (HybriD)" is to develop a software-based analysis tool that helps experts to better assess disinformation campaigns. The interdisciplinary team of computer scientists, communication scientists and IT security service providers combines machine learning with human expertise to identify disinformation campaigns. The analysis tool will make it possible to evaluate large volumes of data from online media and social networks in real time and to detect temporal patterns. Using this database, experts can comprehensively assess disinformation campaigns and their impact. These findings are then returned to the tool, allowing new patterns to be learned. Iteratively, general statements about disinformation patterns can be made and so-called "archetypes" of disinformation can be identified. This is intended to answer the question given at the outset about the emergence and spread of disinformation as well as the possibilities for action.