Link Analysis of Conflict through Signed Spectral Embedding: The Russo-Ukrainian War
Bibliographic record
Abstract
In military intelligence, link analysis is a tool used to review relationships between individuals or groups for insight. The difficulty of accurately depicting complex relationships in link diagrams increases as the number of actors and their activities grows. To address this challenge, we explore the use of spectral embedding as an automated approach, which is capable of preserving the intricate details when presenting relationships as graphs. While spectral embeddings are commonly employed to understand implicit structures in social networks, they are conventionally used in networks with single-weighted edges. We build upon our previously developed spectral embedding technique that allow signed edges to represent both negative and positive relationships. Once networks are represented in lower-dimensional spaces, they can be presented as link diagrams, where the geometric proximity between nodes approximates their similarity. We demonstrate the application of this intelligence tool by automatically generating armed-conflict link diagrams in a study of the Russo-Ukrainian War. By placing each entity in an embedded space, this technique enables the detection of clusters, provides quantifiable assessments, and offers a visual representation of the conflict dynamics. This work showcases the potential of using spectral embedding to enhance our understanding of real-life complex social networks, contributing to more informed decision-making in conflict analysis and management.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".