Trajectories of Conflict: The Dynamics of Argumentation in the UN Security Council
Lead Research Organisation:
University of Dundee
Department Name: Computing
Abstract
Conflict is inherently dynamic. Positions morph, contexts change, factions and allegiances realign, and even when everything else appears to be in stasis, there is change in the language used to express conflict - in the framings and nuances and emotions. Our aim is to understand this dynamism and to test that understanding at scale.
We will develop novel, integrative theory and then apply that theory both to understand ways in which conflict is presented linguistically and also how it evolves, not just in terms of its underlying positions but also in its presentation. We eschew domain- or theme-specific conflict, and instead site our study within the foremost venue for conflict of the highest level and greatest import: the UN Security Council. Rather than focus on a single issue or region or period of the Security Council, our goal is to work with the entirety of its activity in which significant conflict is presented: a dataset of almost one million words. Across the 25 years of almost daily meetings, our techniques will offer insight both to geopolitical analysts and to the general public into how conflicts at the Council emerge and evolve, combining analysis of local discourse features such as vagueness and emotionality with structural features such as justification-giving and patterns of reasoning, and finally considering how positions in conflict are framed. Across all of these aspects there are interacting dynamics, which our theory of conflict trajectories aims to understand so that it will become possible for the first time to map the language of conflict simultaneously in great detail and at very large scale.
This is the first time that the techniques of big data have driven the study of the language of conflict. Though we will bring such computational techniques to bear, our focus is on delivering the foundational theory, the analytical techniques and the dataset resources that can subsequently underpin future computational research and indeed into applied innovation delivering value for scholars of political science, international relations and as well as for professionals working in diplomacy and geopolitical analysis and ultimately the general public.
We will develop novel, integrative theory and then apply that theory both to understand ways in which conflict is presented linguistically and also how it evolves, not just in terms of its underlying positions but also in its presentation. We eschew domain- or theme-specific conflict, and instead site our study within the foremost venue for conflict of the highest level and greatest import: the UN Security Council. Rather than focus on a single issue or region or period of the Security Council, our goal is to work with the entirety of its activity in which significant conflict is presented: a dataset of almost one million words. Across the 25 years of almost daily meetings, our techniques will offer insight both to geopolitical analysts and to the general public into how conflicts at the Council emerge and evolve, combining analysis of local discourse features such as vagueness and emotionality with structural features such as justification-giving and patterns of reasoning, and finally considering how positions in conflict are framed. Across all of these aspects there are interacting dynamics, which our theory of conflict trajectories aims to understand so that it will become possible for the first time to map the language of conflict simultaneously in great detail and at very large scale.
This is the first time that the techniques of big data have driven the study of the language of conflict. Though we will bring such computational techniques to bear, our focus is on delivering the foundational theory, the analytical techniques and the dataset resources that can subsequently underpin future computational research and indeed into applied innovation delivering value for scholars of political science, international relations and as well as for professionals working in diplomacy and geopolitical analysis and ultimately the general public.
Publications

Hautli-Janisz A
(2022)
Disagreement space in argument analysis

Hautli-Janisz A.
(2022)
Disagreement space in argument analysis
in 1st Workshop on Perspectivist Approaches to Disagreement in NLP, NLPerspectives 2022 as part of Language Resources and Evaluation Conference, LREC 2022 Workshop

Reed C
(2021)
IfCoLoG Journal of Logics and their Applications
in The Waltonian Foundations of Argument Technology

Reed C.
(2021)
The waltonian foundations of argument technology
in Journal of Applied Logics
Description | Conflict at the UNSC is different to conflict elsewhere, and annotators struggle to identify instances of conflict in the way they would elsewhere. The connections between background knowledge (in this case, of geopolitical relations) and interpretation of given arguments is even more complex than we had thought. Neither linguistic rhetorical structure nor argumentative reasoning structure alone suffice -- we need principled ways of formulating background knowledge in order that conflict can be reliably determined. |
Exploitation Route | We are currently seeking to work with funders to develop more robust methods for data journalism coming from fora such as the UNSC, using what we have learnt about conflict structure and its highly contextualised nature. |
Sectors | Communities and Social Services/Policy Government Democracy and Justice |
Title | UNSC Pilot Corpus |
Description | Analysis of argumentation and conflict in the UN Security Council |
Type Of Material | Database/Collection of data |
Year Produced | 2022 |
Provided To Others? | Yes |
Impact | none |
URL | http://corpora.aifdb.org/UNSCPilotCorpus |
Title | UNSC WPS |
Description | Analysis from the UN Security Council, Women, Peace & Security debates. Second round analysis with more rigorous conflict analysis. |
Type Of Material | Database/Collection of data |
Year Produced | 2023 |
Provided To Others? | Yes |
Impact | None yet |
URL | http://corpora.aifdb.org/UNSCwps |
Description | Dundee-Passau |
Organisation | University of Passau |
Country | Germany |
Sector | Academic/University |
PI Contribution | Collaborating on large-scale analysis of BBC data |
Collaborator Contribution | Collaborating on large-scale analysis of BBC data |
Impact | 10.1016/j.pragma.2021.10.029 Artificial Intelligence, Pragmatics, Linguistics, Philosophy |
Start Year | 2021 |
Description | Dundee-Potsdam |
Organisation | University of Potsdam |
Country | Germany |
Sector | Academic/University |
PI Contribution | Data, annotation, guidelines and theoretical definitions of conflict |
Collaborator Contribution | Data, annotation and guidelines |
Impact | none |
Start Year | 2021 |
Description | Pindex video |
Form Of Engagement Activity | A broadcast e.g. TV/radio/film/podcast (other than news/press) |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Public/other audiences |
Results and Impact | A youtube video produced by Pindex and narrated by Stephen Fry discussing the need for argument technology and the work of the Centre, 02 October 2021 (250,000 views) |
Year(s) Of Engagement Activity | 2021 |
URL | https://www.youtube.com/watch?v=7cN3rZ5h3LE&ab_channel=Pindex |
Description | Resonance FM |
Form Of Engagement Activity | A press release, press conference or response to a media enquiry/interview |
Part Of Official Scheme? | No |
Geographic Reach | National |
Primary Audience | Public/other audiences |
Results and Impact | Pre-recorded interview included in Future Intelligence's PassWord 9 June 2021 broadcast on Resonance FM (national UK radio, programme audience 750,0000) with accompanying online copy |
Year(s) Of Engagement Activity | 2021 |
URL | https://www.futureintelligence.co.uk/2021/06/09/big-tech-data-scraping-to-discover-our-emotions/ |