World Chaos Map Docs
Loading...
Open map

Confidence Scores

Confidence measures how much we trust a country's pressure score — not the score itself. A high-confidence "Stable" means genuinely low activity. A low-confidence "Stable" means we might just not be seeing what's happening.

📊 6 factors 🎯 4 confidence tiers 🔄 Updated every cycle 🌐 Per-country granularity
The labels you see on the map

Every country page shows how well sourced its score is:

  • Well sourced (high confidence): many independent outlets, most days.
  • Partly sourced (medium): some independent reporting, gaps filled from the last known level, or the stories that carry most of the score carried by only one outlet so far. Since 30 October we judge this on the main stories behind the score, not on every small item. A country whose minimum score comes from deaths recorded by UCDP is at least Partly sourced, because that minimum rests on official data.
  • Thinly sourced (low): very little reporting. Treat the score as a rough estimate.

These labels describe the evidence behind a score, not whether events happened. A war can be Partly sourced when most of its stories come from one local outlet.

Each story behind a score has its own label:

  • Verified: carried by an official source (USGS, GDACS, WHO, ReliefWeb, UCDP) or by three or more independent outlets, or two top-tier ones.
  • Developing: carried by two independent outlets, or one top-tier outlet (a wire service or public broadcaster), so far.
  • Single source: only one outlet so far. It still counts, but less. Claims such as a coup, a nuclear strike or a declaration of war count at 40% until a second outlet carries them.
Why confidence matters

A pressure score without confidence is misleading. Consider two countries both scoring 15 (Stable):

High confidence
15
Stable

12 independent sources, 40+ events analyzed in last 30 days, strong English-language coverage. Score is trustworthy — the country is genuinely quiet.

Low confidence
15
Stable

2 sources, 3 events in 30 days, mostly non-English media. Score may under-report — instability could exist but isn't reaching our feeds.

Confidence factors

Six signals combine to produce a per-country confidence percentage. They are listed from most to least important. Each factor contributes independently — a country can have great source coverage but poor dedup certainty.

Source count

How many independent feeds cover this country. More sources mean better cross-validation and reduced single-source bias. Countries like the US or UK have 15+ dedicated feeds; small island nations may have 1-2.

Event volume (30d)

Total classifiable incidents in the trailing 30-day window. Higher volume means the scoring model has more data points. Zero events in 30 days significantly drops confidence — it could mean peace or it could mean blindness.

Attribution accuracy

How reliably incidents map to the correct country. The NLP engine assigns country roles (location, actor, subject, mentioned) and geographic misattribution filters catch errors. Countries frequently confused with others (e.g., Georgia state vs. country) score lower.

Deduplication certainty

How well the dedup engine handles this country's feed mix. When multiple sources report the same event, dedup must cluster them correctly. Countries with many feeds in different languages are harder to dedup, reducing certainty.

Language coverage

Whether the system has feeds in the country's primary language(s). English-dominant countries score highest. Countries with feeds only in non-supported languages rely on international wire coverage, which skews toward major events.

Recency of updates

How recently the system received data from this country's sources. Feeds that haven't returned new content in 7+ days signal potential staleness. Circuit-broken sources also reduce this factor.

Confidence tiers

The continuous 0–100% score maps to four interpretive tiers:

High (Well sourced)
80–100%

Major nations with extensive English-language media, multiple wire services, and dedicated local feeds. Scores are representative of actual conditions.

United States United Kingdom India Australia Israel Ukraine
Medium (Partly sourced)
50–79%

Regional powers with mixed-language coverage. International wire services cover major events, but local unrest or minor incidents may not reach the pipeline.

Brazil Indonesia Mexico Thailand Kenya Turkey
Low (Thinly sourced)
20–49%

Smaller nations with limited international reporting. Coverage depends heavily on ReliefWeb and regional wire services. Scores may undercount localized instability.

Tajikistan Comoros Lesotho Suriname Timor-Leste
Minimal
<20%

Isolated territories, censored regions, or areas with near-zero international media presence. Scores are unreliable — "Stable" often means "invisible", not "safe".

Bouvet Island Pitcairn Tokelau Turkmenistan Eritrea
Confidence vs. source credibility

These are related but distinct systems:

Confidence
  • Per-country metric
  • Answers: "Can we trust this score?"
  • Based on coverage breadth and depth
  • Shown to users as interpretive context
  • Does not change the pressure score
Source credibility
  • Per-feed metric
  • Answers: "Can we trust this source?"
  • Based on reliability, yield, and dedup survival
  • Used internally by the scoring pipeline
  • Directly dampens severity from low-quality feeds

A country can have high confidence (many feeds) but include some low-credibility sources. The credibility system handles the per-source quality; confidence captures the overall picture.

What boosts confidence

Several pipeline features automatically improve confidence where conditions are met:

🔗
Multi-source corroboration

When 2+ independent sources report the same event (detected via semantic dedup), confidence goes up. This cross-validation is the strongest confidence signal.

📡
Structured API coverage

Countries with data from USGS, GDACS, or ReliefWeb structured APIs get a baseline confidence floor. These APIs are machine-readable and highly reliable.

🌐
Language diversity

Having feeds in both English and the local language improves coverage of both international and domestic events, boosting the language coverage factor.

⚡
Feed freshness

Sources that consistently return fresh content within each 4-hour cycle demonstrate active, reliable coverage — increasing the recency factor.

Reading scores with confidence

Use this matrix to interpret pressure scores in context:

Stable (0–29)
Moderate (30–59)
Unstable (60–84)
Severe (85–100)
High conf.
Genuinely calm
Active tensions detected
Significant crisis likely
Major crisis confirmed
Med conf.
Probably calm
Tensions likely, some gaps
Crisis ongoing, gaps possible
Major crisis, may be worse
Low conf.
Possibly calm, gaps likely
Uncertain — limited data
Crisis signals reaching feeds
Severe — likely undercount
Countries with media restrictions, internet shutdowns, or non-English primary languages tend to have lower confidence scores. This is a data limitation, not a judgment about the country.
Known limitations
  • English bias — The system has stronger coverage in English-speaking countries. Multilingual detection helps but doesn't fully close the gap.
  • Wire service dependency — For many countries, international coverage comes from 2-3 wire services (Reuters, AP, AFP). If they don't cover an event, it's invisible.
  • Internet shutdowns — Governments that cut internet during crises reduce feed output precisely when coverage matters most, creating paradoxical confidence drops during real events.
  • Conflict asymmetry — Active war zones often have high confidence despite being dangerous to report from, because international media focus compensates for local access issues.
  • Small-state noise — Very small countries (populations under 100K) can see confidence swing dramatically from a single feed going offline.

See the sources

View and search the news feeds and official sources behind the scores.