Research

Our research is concerned with the computational linguistic modeling of discourse, rhetorical strategies and argumentation in naturally spoken communication. Depending on the application area and task, we use a variety of methods from Natural Language Processing, from rule-based to stochastic and neural approaches for modeling semantic and pragmatic information in dialogical settings.

Our work is funded by currently two research projects:

• Linguistic Analysis of Public Service Encounters (DFG, EXC Politics of Inequality, University of Konstanz, until 07/23, PhD student: Wassiliki Siskou)
  The project systematically studies the face-to-face interactions between public administrators and citizens, developing a computational linguistic model for measuring administrative language in one-on-one encounters, a novel task in Political Science as well as Computational Linguistics. 

• Deliberation Laboratory (VolkswagenStiftung, AI and the future of society, until 07/24, PhD student: Zlata Kikteva) 
  With DeLab we develop a transformative online testing environment that allows us to explain the nature, causes, and consequences of citizens’ perceptions in deliberative public, online dialogue across languages. By developing a virtual moderator that can follow different cultural scripts, we are able to test the conditions under which citizens and groups evaluate what they see as trustworthy and believable in online communication. 

Past projects include the ADD-up project (Augmented Deliberative Democracy), also supported by the VolkswagenStiftung (until 12/21).