Simula@BI: Explaining News Spreading Phenomena in Social Networks
Speaker: Daniel Thilo Schroeder, PhD-candidate.
- Starts:13:30, 23 September 2021
- Ends:14:30, 23 September 2021
- Price:Open participation
- Contact:Siri Johnsen (firstname.lastname@example.org)
Digital wildfires are fast spreading online misinformation phenomena with the potential to cause harm in the physical world. They have been identified as a considerable risk to developed societies which raised the need to better understand online misinformation phenomena to mitigate that risk. We approach the problem from an interdisciplinary angle with the aim of using large scale analysis of social network data to test hypotheses about the behavior of social network users interacting with misinformation. We discuss state of the art techniques for capturing large volumes of communication data from social networks such as Twitter as well as collections of news such as GDELT. Based on that we describe new methods on how the reach as well as the typical target audience of media and social network participants can be measured. Doing so allows the testing of hypotheses such as the existence of filter bubbles through the use of large amounts of real-world data. Finally we discuss how the detection of anomalies in the typical news spreading patterns can be used to detect disinformation campaigns and digital wildfires.
About the speaker
Daniel Thilo Schroeder is a third-year Ph.D. student at the Technical University of Berlin in cooperation with the Simula Research Laboratory and the Simula Metropolitan Center for engineering in Oslo Norway. He received a master's degree in computer science from the Technical University of Berlin working on large-scale data processing engines for distributed machine learning. His current research targets the network-based examination of news spreading phenomena. Moreover he is interested in accelerator programming distributed systems specifically distributed data types.
Daniel´s homepage: https://www.simula.no/people/daniels
About the Simula@bi Research Seminars
The research seminars in data science will consist of talks on fundamental and applied research within statistics, machine learning and artificial intelligence.