Methodology

The Barometer evaluates the vulnerability of each Wikipedia page across three dimensions: Heat, Quality, and Behaviour. Each metric is normalised between 0 and 1 using functions that are robust to extreme values.

Outlier-robust scoring

Outlier-robust scoring

Raw metrics follow long-tail distributions. A median Z-score (MAD) resists outliers, then a hyperbolic tangent bounds the result between 0 and 1.

// normalisation

Z = (x − x̃) / (1.4826 · MAD)

s = tanh(Z / k)

k ∈ [5, 7]

Alert Thresholds

Healthy0 – 25%
Moderate25 – 75%
Critical75 – 100%

Metrics by dimension

View spikes×5
s = max(0, tanh(Z / 7))

Compares current traffic to historical volatility via a robust Z-score. May flag media events or manipulation campaigns.

Edit spikes×4
s = tanh(Z / 5)

Detects sudden surges in editing activity. An abnormal spike may reveal coordinated vandalism.

Edit war×4
s = 1 − |Σ δᵢ| / Σ|δᵢ|

Measures mutual reversions between contributors. A high score may indicate an editorial deadlock or a polarised conflict between editors.

Revert probability×3

Wikipedia's ML model (ORES/Lift Wing) score indicating whether recent edits are potentially malicious.

Discussion intensity×1
s = tanh(N_msg / K)

Volume of recent messages on the talk page. Intense debate reflects an active editorial controversy.

Staleness×2
s = tanh(D₅ / 30)

Identifies pages with no recent activity, more vulnerable to uncorrected errors.

Protection Level×2

Protection level assigned by Wikipedia administrators. A protected page reflects a history of editorial conflicts.

Alerts

Six alerts trigger automatically when a critical threshold is crossed.

Edit Spike

Abnormal editing activity

View Spike

Sudden traffic explosion

Anonymity

Majority of IP edits

Suspicious Sources

Disinformation domains

Sockpuppets

Sockpuppet accounts active

Edit war

Mutual reversions detected

Data Collection

RevisionsLast 500 revisions — author, diff size, revert probability (ORES/Lift Wing)
ViewsDaily statistics over 90 days via the Wikimedia Pageviews API
MetadataProtection level, Featured Article status, talk pages
SourcesExternal links and domains referenced in the wikitext
SockpuppetsBanned accounts identified by Wikipedia community investigations

Methodology developed as part of the PROMPT project, funded by the European Commission (grant agreement CNECT/LC-02629302). Weights and thresholds are empirically calibrated on a corpus of French and English Wikipedia pages.