Conflict Early Warning · Media Environment Threat Assessment

PRISM — Polarization Risk & Information Stability Metric

This isn't a bias chart. It measures how dangerous an information environment actually is and where it's heading. Validated against documented pre-conflict cases including Rwanda, Myanmar, and the 2022 Russian invasion of Ukraine.

No data loaded
Anchors: 0
Outlets: 0
Reading this dashboard:
Threat gauge = overall danger level. Five cards = what's driving it. Pattern match = which historical crisis this resembles. Trajectory chart = is it getting worse?
GDELT Live Search
Dashboard
At-a-Glance Assessment
Threat Assessment
--
No data
Composite threat level derived from 5 sub-metrics. Grounded in Stanton (genocide stages), Benesch (dangerous speech), Mueller & Rauh (text-based prediction), and Jamison et al. (sentiment spikes).
--
Polarization
How divided is the media ecosystem?
--
Narrative Divergence
Are outlets covering the same reality?
--
Source Diversity
How many voices shape the narrative?
--
Echo Chamber
How siloed is the audience?
--
Acceleration
Is it getting worse faster?
Outlet Spectrum
Historical Pattern Match
Load data to compare against known pre-conflict trajectories
Geographic View
Citation Network
Citation Profile Comparison
Compare outlets: Hold Ctrl/Cmd to select up to 5
Citation Flow
Historical Trajectory Comparison
Scenario Simulator

Model an intervention: what happens to the threat level if you add a new outlet to the ecosystem?

0.00
Trend Analysis
Threat Model Weights
w1 Polarization0.20
w2 Narrative Divergence (NCI)0.25
w3 Entropy Collapse (1-H)0.20
w4 Cross-Exposure Deficit0.15
w5 Escalation Velocity0.20
MPI: -- | NCI: -- | H: --
XD: -- | Vel: -- | Accel: --
Data Input
Configure Analysis
Ecosystem
Name Region Period
Left Pole Right Pole

Define reference entities (think tanks, parties, factions, institutions) with known ideological positions. Position: -1 (left pole) to +1 (right pole).

Define media outlets to analyze. Audience is relative weight (e.g., millions of viewers/readers).

Enter citation counts: how many times each outlet cited each anchor entity during the analysis period.

Add anchors and outlets first to generate the citation matrix.

Paste CSV data below. Format: Outlet, Audience, Anchor1, Anchor2, ...

First row must be headers. Subsequent rows contain outlet data with citation counts per anchor.

Methodology
Note: This is a media environment threat assessment tool, not a media bias chart. It measures ecosystem-level dynamics and their correlation with conflict trajectories. Sample datasets are illustrative. Historical pattern data is derived from published academic research but represents characteristic patterns, not exact empirical measurements.

What makes this different from Ad Fontes or AllSides

Ad Fontes and AllSides answer: "How biased is this outlet?" This tool answers: "How dangerous is this information environment, and where is it heading?" The unit of analysis is the ecosystem, not the outlet. The output is predictive, not descriptive. And the framework is grounded in conflict studies, not media literacy.

1. Slant Quotient (SQ) — Per-Outlet Position

Adapted from Groseclose & Milyo (2005). Each outlet is scored [-1, +1] based on its citation patterns of anchor entities with known positions, using IDF weighting to discount universally-cited sources.

SQm = Σj(wj · pmj · rj) / Σj(|wj · rj|)

2. Polarization Score — Ecosystem Dispersion

Audience-weighted standard deviation of SQ scores, normalized to [0-100]. Measures whether the ecosystem is clustered (healthy) or bimodal (polarized).

MPI = sqrt(Σm(audm · (SQm - SQ̄)²) / Σ audm) × 100

3. Narrative Convergence Index (NCI) — Parallel Realities

Derived from Mueller & Rauh (2018, APSR) who found that the disappearance of shared topics (diplomacy, trade, judiciary) is more predictive of conflict onset than the presence of conflict topics. NCI measures pairwise cosine similarity of outlet citation profiles.

NCI = (1 - avg pairwise cosine similarity) × 100 Low = shared reality | High = parallel information universes

4. Information Entropy (H) — Source Diversity

Shannon entropy of ecosystem-wide citation distribution. Based on the Yugoslavia pattern: Milosevic controlled 95% of Serbian media by 1989 (Fogg, W&M; MOM Serbia). Low entropy = state capture or monopoly narrative.

H = -Σ(pj · log2(pj)) / log2(N) × 100 Low = captured ecosystem | High = healthy pluralism

5. Cross-Exposure Deficit (XD) — Echo Chambers

Derived from the Myanmar finding: 98% of social media users were on Facebook, and algorithmic reinforcement created sealed information bubbles (Yale Macmillan Center, 2024). XD measures the audience-weighted extremity of media consumption.

XD = Σ(audm · |SQm|) / Σ audm × 100

6. Escalation Velocity & Acceleration

Jamison et al. (2023, SSRN) found that media sentiment spikes, not levels, are the strongest short-term conflict predictors (AUC 86-94%). This metric captures the rate and acceleration of polarization change.

7. Composite Threat Level

Five-factor model with weights calibrated from case literature. The public showcase demonstrates the framework; full calibration parameters, pattern matching trajectories, and proprietary weighting schemas are available under commercial license.

Threat = f(Polarization, Narrative, Entropy, Exposure, Velocity) where each factor is weighted by coefficients derived from empirical analysis of documented pre-conflict media environments

Threat levels are aligned with Stanton's Ten Stages of Genocide and Benesch's Dangerous Speech Framework:

RangeLevelInterpretationHistorical Pattern
0-20NormalHealthy media competitionCanada/Germany baseline
20-40WatchPolarization trends detectedEarly divergence signals
40-60WarningNarrative fragmentation acceleratingEthiopia 2019, Myanmar 2020
60-80AlertPre-conflict media patterns detectedYugoslavia 1991, Myanmar 2021-Q1
80-100CriticalMedia environment resembles onset conditionsRwanda 1994, Yugoslavia 1992

8. Historical Pattern Matching

The tool compares the current ecosystem's [Polarization, NCI, Entropy, Echo, Velocity] vector against reconstructed trajectories from five documented cases: Rwanda (Yanagizawa-Drott 2014, Roozen & Shulman 2014), Myanmar (Yale Macmillan 2024), Yugoslavia (Fogg, PBS Frontline), Ethiopia (Nigussie et al. 2024), and a stable democracy baseline. Pattern matching uses normalized Euclidean distance.

References

Foundational
Groseclose, T. & Milyo, J. (2005). A Measure of Media Bias. QJE, 120(4).
Mueller, H. & Rauh, C. (2018). Reading Between the Lines. APSR, 112(2).
Yanagizawa-Drott, D. (2014). Propaganda and Conflict. QJE, 129(4).
Benesch, S. (2014). Countering Dangerous Speech. USHMM Working Paper.
Stanton, G. (2016). Ten Stages of Genocide. Genocide Watch.
Hegre, H. et al. (2019). ViEWS: A Political Violence Early-Warning System. JPR, 56(2).

Case Studies
Roozen, K. & Shulman, S. (2014). Tuning in to the RTLM. Conflict & Communication.
Nigussie, D. et al. (2024). Echoes of Violence: Hate Speech in Ethiopian Media. SAGE.
Jamison, A. et al. (2023). Media Sentiment and Future Conflict Events. SSRN.

2025-2026 (Cutting Edge)
Petrova, M. & Tapsoba, A. (2025). Information and Conflict. Economic Policy, Oxford.
Piccardi, T. et al. (2025). Reranking Partisan Animosity Alters Polarization. Science.
EPJ Data Science (2025). Predicting Collective Violence Through Hostile Social Media Discourse.
STFT-VNNGP (2025). Forecasting Geopolitical Events with Sparse Temporal Fusion Transformer. arXiv.
VIEWS/PRIO (2025-2026). Violence & Impacts Early-Warning System monthly forecasts.
ACLED (2026). Conflict Index & 2026 Watchlist.

Export

Your analysis is ready.

Enter your email to receive the full polarization assessment with PRISM score, instability classification, conflict-pattern comparison, and methodology documentation.

Need this applied to your media environment?

Commission a full media polarization assessment with custom outlet data, calibrated anchor entities, historical trend analysis, and conflict-pattern comparison. Available for media monitoring organizations, peacebuilding NGOs, government agencies, and research institutions.

Commission Assessment →