DISINFORMATION ANALYSIS
Generally availableDetect manipulation techniques - not political viewpoints.
Sentiqra identifies how a text manipulates - fabricated claims, urgency amplification, conspiracy framing - across 16 languages. It never scores which side of an argument is right.
200 labels · 16 languages · p95 target <500ms · Every result reproducible
Mechanism-level signals - the claim's content is never scored for truth
What this analyzer does and doesn't do
- Detect manipulation techniques: fabrication, urgency, conspiracy framing, evasion
- Flag coordination signals in high-volume text streams
- Cover 16 languages with per-language evaluation
- ✕Decide which political viewpoint is correct
- ✕Fact-check or confirm the truth of any claim
- ✕Score individuals, outlets, or parties for credibility
- ✕Make removal or demonetization decisions
Sentiqra returns structured signals. Your policy, reviewers, and models make the decision. See the full boundary statement →
WHAT YOU'LL DETECT
51 documented propaganda techniques - in plain English.
Information Integrity
fabricated_claim
Asserting invented events as settled fact
Emotional & Social Manipulation
scarcity_pressure
“Share before it gets deleted”
Conspiracy & Hidden Agency
conspiracy_claim
“Ask yourself who benefits”
Suppression & Distraction
agenda_diversion
Redirecting scrutiny to an unrelated wrong
Polarization & Othering
dehumanization
Stripping a group of human attributes
87.3% – 100% Production Top-3 Hit Rate across 16 languages.
Benchmarks vary by language - the range above is the honest spread, not the best case. Top-3 Hit Rate means the expected label appears among the 3 highest-confidence signals returned; it measures ranking quality, not whether a thresholded accept/reject decision was right.
WHERE IT GETS USED
Three jobs this analyzer does well.
Platform integrity during elections
A platform integrity team screens election-period content for manipulation mechanics - fabricated claims, engineered urgency, conspiracy framing - while leaving viewpoint scoring entirely out of scope. Every flag is a mechanism label a reviewer can verify, not an opinion about politics.
Fit signals: election cycles · policy-defensible labels · high-scrutiny moderation
Coordinated influence campaign detection
A research team tracks recurring technique signatures across accounts and languages. Because outputs are deterministic and config-pinned, the same campaign material reproduces the same signal profile weeks apart - letting analysts correlate waves instead of re-litigating scores.
Fit signals: cross-language campaigns · longitudinal tracking · reproducible correlation
Fact-check queue prioritization
A newsroom verification desk orders incoming tips by manipulation-technique density rather than gut feel. Fabricated-claim and urgency signals push the highest-risk items to the top; the signed receipt on each item survives editorial review.
Fit signals: limited reviewer hours · defensible prioritization · newsroom workflows
Send candidate content. Get technique signals + a receipt.
POST /v1/analyze
Authorization: Bearer sq_live_your_api_key_here
{
"text": "They don't want you to know the results were fabricated overnight - share before it gets deleted.",
"language": "en",
"analyzers": ["disinformation"]
}{
"language": "en",
"signals": [
{ "analyzer": "disinformation", "code": "manipulation_coordination", "label": "Manipulation & Coordination", "score": 0.9, "confidence": "very_high", "level": "category" },
{ "analyzer": "disinformation", "code": "urgency_amplification", "label": "Urgency Amplification", "score": 0.9, "confidence": "very_high", "level": "label", "parent": "manipulation_coordination" }
],
"meta": { "analyzers": [{ "name": "disinformation", "status": "completed", "signal_count": 2, "billed": true }], "partial": false },
"usage": { "analyzer_runs": 1, "billed": true },
"verification": {
"configuration": "sqcfg_FRA3E88J",
"fingerprint": "fp_8a72...19f",
"input_commitment": "ic_31bd...a42",
"signature": "sig_ed25519_4c1f...e2a"
}
}READING THE OUTPUT
What a Disinformation Analysis result tells you - and what it doesn't.
Intended task
Flag documented manipulation techniques - fake authority, urgency amplification, conspiracy framing - present in a piece of text.
Input requirements
text- the only field analyzed; up to 4,096 Unicode code points. Over the limit is rejected withinput_too_long, never truncated.language- must be a language this analyzer supports. Unsupported codes are rejected with400 unsupported_language, never analyzed as a different language.analyzers- include"disinformation"; up to 2 analyzers per request, one billed run each.- No context beyond
text- no user IDs, history, profiles, or attachments are read or inferred. - Analyzes the submitted text only - author identity, distribution, and source reputation are not inputs.
Ordinary positive
“They do not want you to see these numbers. Every official source is compromised - share this everywhere before it gets deleted.”
Safe inference: The text uses documented manipulation techniques. Queue it for review or downrank it per your integrity policy.
Confusing negative · Quotation
“The viral post claimed "every official source is compromised" - the audit released today shows the figures are real.”
What happens: Manipulation signals can still fire on the quoted claim. Debunks repeat the language they debunk - a signal marks the presence of a technique's vocabulary, not the author's side of the argument.
Why it's tricky: The analyzer detects techniques in text; it never decides which underlying claim is true. Fact-checkers, researchers, and journalists regularly produce text that matches - that is a routing signal, not an accusation.
What you can safely infer
- Which documented manipulation techniques appear in the text.
- That the same text on the same pinned configuration replays identically for your research record.
What you must not infer
- ✕That the author is running an influence operation - technique presence is not attribution.
- ✕That the underlying claim is true or false - truth adjudication is out of scope.
- ✕That text with no signals is trustworthy - a missing signal means "not detected," never "clean."
Boundary: Manipulation signals flag techniques in the text - they are not a verdict on which claim is true and not attribution of an operation.
Disinformation Analysis is on every plan. Even Free.
Free
5,000 runs/mo
Build
$149/mo · 50,000 runs/mo
Growth
$349/mo · 150,000 runs/mo
Production
$799/mo · 500,000 runs/mo
Scale
$2,999/mo · 2,500,000 runs/mo
Enterprise
By agreement · SOC 2 Type II in progress
Deterministic by construction, provable by receipt.
A signed verification receipt - configuration ID (sqcfg_...), result fingerprint (fp2_...), input commitment (ic3_...), and Ed25519 signature (sig_ed25519_...) - ships with every successful analysis result. Pin it to the stored decision and a later replay under the same supported configuration and output profile yields the identical canonical result - the difference between "the model said so" and evidence.
Where it fits in your pipeline
Often paired with: Crisis Intelligence for conflict reporting, Cybersecurity for influence-op infrastructure, Trust & Safety for harmful content alongside manipulation.
Used in: Information Integrity
Test it on content from your last integrity review.
5,000 analyzer runs/month · No card required
Analyzer FAQ
New to Sentiqra? It's a deterministic text-analysis API - you send text, you get labeled, confidence-scored signals plus a replayable receipt. Disinformation Analysis is the information integrity detection analyzer.
What does Disinformation Analysis detect?
Detect propaganda, coordinated influence, synthetic media, evidence manipulation, and narrative operations.
Which languages does it cover?
16 supported languages, each with a published per-language benchmark. Coverage is per-analyzer, not platform-wide - check the language list on this page before assuming parity with other analyzers.
How do I call it?
POST /v1/analyze with "analyzers": ["disinformation"]. Same endpoint, auth, and response shape as every other analyzer - you can pair it with one more analyzer in the same request.
What does a call cost?
One analyzer run per call, billed against your plan's included runs (overage per plan). All GA analyzers are on every plan, including Free - see pricing.
How do I evaluate it on my data?
Label a few hundred of your own examples, run them through the free tier, and compare our signals to your labels. The evaluation playbook walks through building that test set - it's the same method we use internally.