A5050652787- Data Quality and Management
- Political Conflict and Governance
- Data Mining Algorithms and Applications
- Climate change impacts on agriculture
- Advanced Text Analysis Techniques
- Agricultural risk and resilience
- International Development and Aid
- Technology and Data Analysis
- Transboundary Water Resource Management
- Peacebuilding and International Security
- Text and Document Classification Technologies
- Misinformation and Its Impacts
- Social Media and Politics
- Machine Learning and Algorithms
- Data Stream Mining Techniques
- COVID-19 epidemiological studies
- Rangeland Management and Livestock Ecology
- Mathematical and Theoretical Epidemiology and Ecology Models
- Terrorism, Counterterrorism, and Political Violence
- Spam and Phishing Detection
- Computational and Text Analysis Methods
- Opinion Dynamics and Social Influence
- Natural Language Processing Techniques
- Health and Conflict Studies
- Global Peace and Security Dynamics
Uppsala University
2015-2023
To date, the research community has failed to reach a consensus on nature and significance of relationship between climate variability armed conflict. We argue that progress been hampered by insufficient attention paid context in which droughts other climatic extremes may increase risk violent mobilization. Addressing this shortcoming, study presents an actor-oriented analysis drought-conflict relationship, focusing specifically politically relevant ethnic groups their sensitivity...
This article presents ViEWS – a political violence early-warning system that seeks to be maximally transparent, publicly available, and have uniform coverage, sketches the methodological innovations required achieve these objectives. produces monthly forecasts at country subnational level for 36 months into future all three UCDP types of organized violence: state-based conflict, non-state one-sided in Africa. The methodology data behind forecasts, evaluates their predictive performance,...
Although substantive agreement exists on the role of climate variability and food scarcity in increasing violence, a limited number studies have investigated how resources affect violent conflict. This article explores complex linkages between variability, agricultural production conflict onset, by focusing spatial distribution crop cross-country setting. We hypothesize that differences within countries are relevant factor shaping impact agriculturally -dependent countries. To test this...
In this article, we present the most up-to-date, fine-grained, global dataset on external support in armed conflicts: UCDP External Support Dataset (ESD). The encompasses data states and non-state actors as both supporters recipients provides detailed information type of provided to warring parties conflicts between 1975 2017. We use it highlight three broader trends provision support: (1) a dramatic increase number supporters, (2) larger share pro-government interventions, (3) rise direct...
Common political economy models point to rationalist motives for engaging in conflict but say little about how income shocks translate into collective violence some cases not others. Grievance models, contrast, focus on structural origins of shared frustration offer less insight when the deprived decide challenge status quo. Addressing these lacunae, we develop a theoretical model civil that predicts loss trigger violent mobilization primarily shock can be linked preexisting grievances. The...
This article presents an update to the ViEWS political Violence Early-Warning System. introduces (1) a new infrastructure for training, evaluating, and weighting models that allows us more optimally combine constituent into ensembles, (2) number of forecasting contribute improve overall performance, in particular with respect effectively classifying high- low-risk cases. Our improved evaluation procedures allow develop specialize either immediate or distant future. We also present formal,...
Manual coding of political events from news reports is extremely expensive and time-consuming, whereas completely automatic has limitations when it comes to the precision granularity data collected. In this paper, we introduce an alternative strategy by establishing a semi-automatic pipeline, where classification system eliminates irrelevant source material before further done humans. Our pipeline relies on high-performance supervised heterogeneous ensemble classifier working unbalanced...
The spread of Internet and mobile phone access around the world has implications for both processes contentious politics subsequent reporting protest, terrorism, war. In this paper, we explore whether political violent events that occur close to modern communication networks are systematically better reported than others. Our analysis approximates information availability by level detail provided about date each event in Africa from 2008 2010 finds although technology improves reporting,...
Temporally and spatial disaggregated datasets are commonly used to study political violence. Researchers increasingly studying the data generation process itself understand selection processes by which conflict events included in datasets. This work has focused on fatalities. In this research note, we explore how non-fatal reported upon enter into of armed conflict. To do so, compare with population two direct observation datasets, collected using a boots-on-the-ground strategy: mass...
This article presents a new, monthly updated dataset on organized violence—the Uppsala Conflict Data Program Candidate Events Dataset. It contains recent observations of candidate events, majority which are eventually included in the Georeferenced Event Dataset as part its annual update after careful vetting process. We describe definitions, sources and procedures employed to code set issues that emerge when coding data violence near-real time. Together, Datasets minimize an inherent...
High-resolution event data on armed conflict and related processes have revolutionized the study of political contention with datasets like UCDP GED, ACLED etc. However, most these limit themselves to collecting spatio-temporal (high-resolution) intensity data. Information dynamics, such as targets, tactics, purposes are rarely collected owing extreme workload rely a rich corpus textual allowing further mining information connected each event. This paper proposes one approach that is...