An Ordinal Latent Variable Model of Conflict Intensity
Published in Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, 2023
Measuring the intensity of events is crucial for monitoring and tracking armed conflict. In this paper, we propose a generative model that captures the intensity of conflict-related events via an ordinal latent variable. We evaluate the proposed model both intrinsically and extrinsically, showing that it obtains good held-out predictive performance.
Paper Code