Search for: All records

We examine measurement concerns about computer-aided political event data in the state-of-the-art after 2015. The focus is on how to compare and quantify the mathematical and/or conceptual distance between what a machine codes/classifies from information describing an event and the actual circumstances of the event, or theground truth. Three primary arguments are made: (1) It is important for users of event data to understand the measurement side of these data to avoid faulty inferences and make better decisions. (2) Avant-garde event data systems are still not free from some of the fundamental problems that plague legacy systems (investigated are theoretical and real-world examples of measurement issues, why they are problematic, how they are dealt with, and what is left to be desired even with newer systems). (3) One of the most crucial goals of event data science is to attain congruence between what is machine-coded/classified vs. the ground truth. To support these arguments, the literature is benchmarked against well-documented sources of measurement error. Guidance is provided on how to make performance comparisons within and across language models, identify opportunities to improve event data systems, and more articulately discuss and present findings in this area of research. 

Governmental and nongovernmental organizations have increasingly relied on early-warning systems of conflict to support their decisionmaking. Predictions of war intensity as probability distributions prove closer to what policymakers need than point estimates, as they encompass useful representations of both the most likely outcome and the lower-probability risk that conflicts escalate catastrophically. Point-estimate predictions, by contrast, fail to represent the inherent uncertainty in the distribution of conflict fatalities. Yet, current early warning systems are preponderantly focused on providing point estimates, while efforts to forecast conflict fatalities as a probability distribution remain sparse. Building on the predecessor VIEWS competition, we organize a prediction challenge to encourage endeavours in this direction. We invite researchers across multiple disciplinary fields, from conflict studies to computer science, to forecast the number of fatalities in state-based armed conflicts, in the form of the UCDP ‘best’ estimates aggregated to two units of analysis (country-months and PRIO-GRID-months), with estimates of uncertainty. This article introduces the goal and motivation behind the prediction challenge, presents a set of evaluation metrics to assess the performance of the forecasting models, describes the benchmark models which the contributions are evaluated against, and summarizes the salient features of the submitted contributions. 

This article introduces ConfliBERT-Spanish, a pre-trained language model specialized in political conflict and violence for text written in the Spanish language. Our methodology relies on a large corpus specialized in politics and violence to extend the capacity of pre-trained models capable of processing text in Spanish. We assess the performance of ConfliBERT-Spanish in comparison to Multilingual BERT and BETO baselines for binary classification, multi-label classification, and named entity recognition. Results show that ConfliBERT-Spanish consistently outperforms baseline models across all tasks. These results show that our domain-specific language-specific cyberinfrastructure can greatly enhance the performance of NLP models for Latin American conflict analysis. This methodological advancement opens vast opportunities to help researchers and practitioners in the security sector to effectively analyze large amounts of information with high degrees of accuracy, thus better equipping them to meet the dynamic and complex security challenges affecting the region. 

Recent advances in natural language processing (NLP) and Big Data technologies have been crucial for scientists to analyze political unrest and violence, prevent harm, and promote global conflict management. Government agencies and public security organizations have invested heavily in deep learning-based applications to study global conflicts and political violence. However, such applications involving text classification, information extraction, and other NLP-related tasks require extensive human efforts in annotating/labeling texts. While limited labeled data may drastically hurt the models’ performance (over-fitting), large demands on annotation tasks may turn real-world applications impracticable. To address this problem, we propose Confli-T5, a prompt-based method that leverages the domain knowledge from existing political science ontology to generate synthetic but realistic labeled text samples in the conflict and mediation domain. Our model allows generating textual data from the ground up and employs our novel Double Random Sampling mechanism to improve the quality (coherency and consistency) of the generated samples. We conduct experiments over six standard datasets relevant to political science studies to show the superiority of Confli-T5. Our codes are publicly available 

Political and social scientists monitor, analyze and predict political unrest and violence, preventing (or mitigating) harm, and promoting the management of global conflict. They do so using event coder systems, which extract structured representations from news articles to design forecast models and event-driven continuous monitoring systems. Existing methods rely on expensive manual annotated dictionaries and do not support multilingual settings. To advance the global conflict management, we propose a novel model, Multi-CoPED (Multilingual Multi-Task Learning BERT for Coding Political Event Data), by exploiting multi-task learning and state-of-the-art language models for coding multilingual political events. This eliminates the need for expensive dictionaries by leveraging BERT models' contextual knowledge through transfer learning. The multilingual experiments demonstrate the superiority of Multi-CoPED over existing event coders, improving the absolute macro-averaged F1-scores by 23.3% and 30.7% for coding events in English and Spanish corpus, respectively. We believe that such expressive performance improvements can help to reduce harms to people at risk of violence. 

This paper explores three different model components to improve predictive performance over the ViEWS benchmark: a class of neural networks that account for spatial and temporal dependencies; the use of CAMEO-coded event data; and the continuous rank probability score (CRPS), which is a proper scoring metric. We forecast changes in state based violence across Africa at the grid-month level. The results show that spatio-temporal graph convolutional neural network models offer consistent improvements over the benchmark. The CAMEO-coded event data sometimes improve performance, but sometimes decrease performance. Finally, the choice of performance metric, whether it be the mean squared error or a proper metric such as the CRPS, has an impact on model selection. Each of these components–algorithms, measures, and metrics–can improve our forecasts and understanding of violence. 

Knowledge discovery and extraction approaches attract special attention across industries and areas moving toward the 5V Era. In the political and social sciences, scholars and governments dedicate considerable resources to develop intelligent systems for monitoring, analyzing and predicting conflicts and affairs involving political entities across the globe. Such systems rely on background knowledge from external knowledge bases, that conflict experts commonly maintain manually. The high costs and extensive human efforts associated with updating and extending these repositories often compromise their correctness of. Here we introduce CoMe-KE (Conflict and Mediation Knowledge Extractor) to extend automatically knowledge bases about conflict and mediation events. We explore state-of-the-art natural language models to discover new political entities, their roles and status from news. We propose a distant supervised method and propose an innovative zero-shot approach based on a dynamic hypothesis procedure. Our methods leverage pre-trained models through transfer learning techniques to obtain excellent results with no need for a labeled data. Finally, we demonstrate the superiority of our method through a comprehensive set of experiments involving two study cases in the social sciences domain. CoMe-KE significantly outperforms the existing baseline, with (on average) double of the performance retrieving new political entities.