Trajectories of Conflict: The Dynamics of Argumentation in the UN Security Council
The goal of this project is to explore the dynamics of conflict in the domain of international relations, in particular in the debates of the UN Security Council. We want to better understand how language reflects the trajectories of conflicts in those diplomatic exchanges, and thus we undertake formal analyses of discourse structure and argumentation, and track their development over a debate, or across multiple debates on the same topic.
Our work will be based on a recently published digital version of over 20 years of UN Security Council debates (Schönfeld et al. 2019). On this text corpus, we first perform a number of preparatory automatic analysis steps, before attending to subtleties of the argumentation. Both manual coding and automatic text mining techniques will be used, and further enhanced to cover the phenomena in this particular linguistic genre of diplomatic speech.
The DFG/AHRC-funded project is a cooperation between the University of Potsdam and the University of Dundee. The research strategies of these two teams complement each other: With Dundee’s strong background in analysing argumentative dialogue (in particular, via Inference Anchoring Theory) and Potsdam’s focus on identifying monological text structure (in particular, via Rhetorical Structure Theory), the partners are well prepared to work on a genre that is defined by combining features of both dialogue and monologue - viz. political debate with relatively long speeches.
The project’s research questions and methods cut across the disciplines of computational linguistics, philosophy, political science and international studies.
We presented the project in the university's science magazine, Portal Wissen - Zwei 2022 "Mensch" (only in German).
Project Team
Dr. Alexandru Marcoci (University of Dundee)
Dr. Ronny Patz (external advisor, Hertie School Berlin)
Prof. Dr. Chris Reed (University of Dundee)
Prof. Dr. Manfred Stede (University of Potsdam)
Karolina Zaczynska (University of Potsdam)
Duration
The project runs from September 2021 to August 2024.
Dataset
Schoenfeld, Mirco; Eckhard, Steffen; Patz, Ronny; Meegdenburg, Hilde van; Pires, Antonio, 2019, "The UN Security Council Debates", https://doi.org/10.7910/DVN/KGVSYH, (Harvard Dataverse)
Presentations
-
"Analysing the dynamics of conflict in the UN Security Council using inference anchoring theory and rhetorical structure theory" (presenter: Karolina Zaczynska) at COMPTEXT conference, 6–7 May 2022, Dublin, Ireland.
-
"Analyzing Conflict in the UN Security Council: Corpus Linguistics, Rhetorical Structures, and the Ukraine Debates 2014-22 " (presenter: Antonio Pires) at the ISA 2023 Annual Convention, 15-18 March 2023, Montreal, Québec, Canada.
-
"A New Dataset for Analyzing Conflict in the UN Security Council" (presenter: Karolina Zaczynska) at the 16th EISA Pan-European Conference on International Relations, 5-9 September 2023, University of Potsdam, Germany.
Related publications:
- Karolina Zaczynska, Peter Bourgonje, and Manfred Stede. How Diplomats Dispute: The UN Security Council Conflict Corpus. In Proceedings of the Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). Turin, Italy, 2024. URL: https://github.com/linatal/UNSCon. [Bibtex] [PDF]
- Karolina Zaczynska and Manfred Stede. Rhetorical Strategies in the UN Security Council: Rhetorical Structure Theory and Conflicts. In Proceedings of the SIGDIAL 2024 conference. Kyoto, 2024. (to appear). [Bibtex]
- Stian Rødven-Eide, Karolina Zaczynska, Antonio Pires, Ronny Patz, and Manfred Stede. The UNSC-Graph: An Extensible Knowledge Graph for the UNSC Corpus. In Proceedings of the Workshop on Computational Linguistics for Political Text Analysis (CPSS-2023). Ingolstadt, 2023. [Bibtex] [PDF]
- Luis Glaser, Ronny Patz, and Manfred Stede. UNSC-NE: A Named Entity Extension to the UN Security Council Debates Corpus. Journal for Language Technology and Computational Linguistics, 35(2):51–67, 2022. [Bibtex] [PDF]