Transformer models fine-tuned on dyad-level newswire digests forecast conflict escalation better than a fatality-history baseline at one-month horizons, but lose skill at six months.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
From Newswire to Nexus: Using text-based actor embeddings and transformer networks to forecast conflict dynamics
Transformer models fine-tuned on dyad-level newswire digests forecast conflict escalation better than a fatality-history baseline at one-month horizons, but lose skill at six months.