Workshop Program‎ > ‎


Mike Preuss
Research Associate at ERCIS, University of Muenster, Germany

Title: PropStop: Detecting Propaganda in Social Media, a Multidisciplinary Perspective

AbstractSocial Media has become an important source of information and means of virtual social interaction that nowadays encompasses more than a third of the world's population and is still growing. Recently, we have seen several election campaigns with a surprising outcome (Brexit, US election) and have started to wonder if and how social bots and organized troll action have been involved in Propaganda and opinion manipulation. Even Facebook now acknowledges so-called "information operations". During the last 2 years, the PropStop project has detected and investigated several occurrences of such operations, e.g. in the last weeks before the German general elections of September 2017. We report on the detected incidents and envision how the situation will evolve in the near future.

Short bioMike Preuss is Research Associate at ERCIS, University of Muenster, Germany. Previously, he was with the Chair of Algorithm Engineering at TU Dortmund, Germany, where he received his PhD in 2013. His research interests focus on the field of evolutionary algorithms for real-valued problems, namely on multimodal and multiobjective optimization, and on computational intelligence methods for computer games, especially in procedural content generation (PGC) and realtime strategy games (RTS).
He is also interested in applying the game AI techniques to engineering problems, e.g., chemical retrosynthesis. Since 2016, he is involved in the PropStop project that deals with the detection of Propaganda on social media.
He is associate editor of the IEEE ToG (Transactions on Games) and advisory board member of Springer's Natural Computing book series and has been member of the organizational team of several conferences in the last years, in various functions, as general co-chair, proceedings chair, competition chair, workshops chair, notably also as PC co-chair for CIG 2018.

Huijuan Wang
Delft University of Technology, Netherlands

Title: Modeling of Social Contagion on Networks

AbstractWe have witnessed the explosion of online social networks such as Facebook and YouTube. Each of such online platforms supports the spread of information, opinions and behaviors, the so-called social contagion. However, we lack a foundational understanding about the social contagion mechanisms and how to influence the contagion processes. Take the contagion of opinion and the spread of information on social networks as two examples. I will illustrate the methodologies and progress we have made in modeling and influencing these contagion processes, in periods without and with rich user activity data.

Short bioHuijuan Wang is currently a tenured Assistant Professor in the Multimedia Computing Group at Delft University of Technology. She received the Ph.D. degree (cum laude) in Electrical Engineering from the Delft University of Technology in 2009. She has been a visiting scientist in the Department of Physics at Boston University since 2011 and in the Department of Electrical Engineering at Stanford University in 2015. Her main research areas are performance analysis of complex networks and systems, dynamic processes e.g. viral spreading, opinion formation and cascading failures on multi-layer interconnected networks and networked data analysis. She is the package leader of the FP7 FET project CONGAS (Dynamics and coevolution in Multi-Level Strategic Interaction Games) and the KPN-TUDelft project NExTWORKx on AI Networking.