About Me
I'm a PhD student in Computational Linguistics at the University of Passau and a researcher at Zeppelin University, where I work on the BiASE AI project. I was formerly affiliated with the Exzellenzcluster 'Politics of Inequality' where I worked for the 'Computational Linguistic Analysis of Public Service Encounters' project.
I study language and power asymmetries in institutional dialogue. My dissertation draws on a large corpus of German public service encounters and Californian parole hearing transcripts to analyse the linguistic manifestation of power by e.g. analysing question-answer dynamics. More recently, I have been exploring what Large Language Models can and cannot replicate about human decision-making in high-stakes institutional contexts.
-
Education
2017-2020: Master of Arts in Speech and Language Processing from the University of Konstanz
2013-2017: Bachelor of Arts in Spanish Studies and Economics from the University of Konstanz
-
Professional experience
Sep 2025 - Present: Scientific staff at the Zeppelin University (Friedrichshafen, Germany)
Jan 2022 - Feb 2025: Scientific staff at the University of Passau
Aug 2020 - Aug 2025: Scientific staff at the University of Konstanz
Aug 2018 - Feb 2019: Internship at Daimler AG (Sindelfingen, Germany) Team Navigation Systems
May 2018 - Aug 2020: Research assistant at the University of Konstanz (Germany)
-
Awards
2019 University of Konstanz's Alumni Association (VEUK) prize for outstanding academic accomplishments
-
Associate membership
2022-Present: Centre for Argument Technology (University of Dundee, Scotland, UK)
Publications
-
Exploring the Limits of Prompting LLMs with Speaker-Specific Rhetorical Fingerprints
Wassiliki Siskou and Annette Hautli-Janisz
Proceedings of the First on Natural Language Processing and Language Models for Digital Humanities (LM4DH 2025) PAPER -
"So, are you a different person today?" Analysing Bias during Parole Hearings
Wassiliki Siskou and Ingrid Espinoza
Proceedings of the Second Workshop on Social Influence in Conversations (SICon 2024) PAPER -
Automated Anonymization of Parole Hearing Transcripts
Abed Itani, Wassiliki Siskou, Annette Hautli-Janisz
Proceedings of the Natural Legal Language Processing Workshop 2024 PAPER -
PSE v1.0: The First Open Access Corpus of Public Service Encounters
Ingrid Espinoza, Steffen Frenzel, Laurin Friedrich, Wassiliki Siskou, Steffen Eckhard, Annette Hautli-Janisz
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) PAPER -
Measuring plain language in public service encounters
Wassiliki Siskou, Laurin Friedrich, Steffen Eckhard, Ingrid Espinoza, Annette Hautli-Janisz
Proceedings of the 2nd Workshop on Computational Linguistics for Political Text Analysis (CPSS-2022) Potsdam, Germany. PAPER -
Automatized Detection and Annotation for Calls to Action in Latin-American Social Media Postings
Wassiliki Siskou, Clara Giralt MirĂ³n, Sarah Molina-Raith, and Miriam Butt
Proceedings of the 6th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature. International Conference on Computational Linguistics, 2022. PAPER -
Annotating very large arguments
Kamila Gorska, Wassiliki Siskou, and Chris Reed
Computational Models of Argument: Proceedings of COMMA 2022. editor / Francesca Toni ; Sylwia Polberg ; Richard Booth ; Martin Caminada ; Hiroyuki Kido. IOS Press BV, 2022. pp. 357-358 (Frontiers in Artificial Intelligence and Applications). PAPER -
The Keystone Role Played by Questions in Debate
Zlata Kikteva, Kamila Gorska, Wassiliki Siskou, Annette Hautli-Janisz, and Chris Reed
In Proceedings of the 3rd Workshop on Computational Approaches to Discourse, at COLING 2022, 2022. PAPER -
QT30: A Corpus of Argument and Conflict in Broadcast Debate
Annette Hautli-Janisz, Zlata Kikteva, Wassiliki Siskou, Kamila Gorska, Ray Becker, and Chris Reed
In Proceedings of the Thirteenth Language Resources and Evaluation Conference (LREC 2022), European Language Resources Association, 2022. PAPER