RISK GROUPS REFERENCE
Dating Safety Risk Groups
Dating Safety organizes detection into 5 risk groups covering 200 indicators across 40 languages.
All Risk Groups
Each risk group contains a set of specific indicators that the API can detect. Click a group to expand its signal list. Signal lists are available to customers - sign in to view them.
01
Deception Manipulation
deception_manipulation
50
50 signals - request access
for the complete list.
View 50 indicators
Deception Manipulation
deception_manipulation
The complete signal list is available to customers. Request access to view it.
02
Abuse Threats
abuse_threats
50
50 signals - request access
for the complete list.
View 50 indicators
Abuse Threats
abuse_threats
The complete signal list is available to customers. Request access to view it.
03
Sexual Boundaries
sexual_boundaries
30
30 signals - request access
for the complete list.
View 30 indicators
Sexual Boundaries
sexual_boundaries
The complete signal list is available to customers. Request access to view it.
04
Exploitation
exploitation
30
30 signals - request access
for the complete list.
View 30 indicators
Exploitation
exploitation
The complete signal list is available to customers. Request access to view it.
05
Platform Misc
platform_misc
40
40 signals - request access
for the complete list.
View 40 indicators
Platform Misc
platform_misc
The complete signal list is available to customers. Request access to view it.
Reading Dating Safety output
What you can safely infer from a result - and what you must not.
Intended task
Flag documented dating-risk patterns - scam lures, coercion, unsafe-contact escalation - in member text for review and warning flows.
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"dating-safety"; 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 message only - profiles, photos, match history, and payment records are not inputs.
Ordinary positive
“My love, the customs office is holding your package. I need EUR 400 for the release fee - can you send it today?”
Safe inference: The message matches documented romance-scam and money-request patterns - route it to the specialized queue before money moves.
Confusing negative · Quotation
“He wrote "the customs office is holding your gift - I need EUR 400 for the release fee" - is this a scam?”
What happens: Scam signals can still fire: the member is quoting the lure to report it, but the analyzer scores the submitted text as written. The signal means the text contains documented scam language - not that the sender of this message is a scammer.
Why it's tricky: Reports, safety warnings, and appeals all quote the messages they describe. Combine the signal with who sent the text and your own context - and remember that a bare "can you send me money?" may be too thin to match strongly. Absence is "not detected," never clearance.
What you can safely infer
- Which documented risk behaviors the text matched, and at what signal-match strength.
- That the receipt ties each flag to the configuration that produced it - a replayable record for investigators.
What you must not infer
- ✕That the sender is actually a scammer - the signal describes the text, not the person.
- ✕That the recipient is a victim or that a reported incident occurred.
- ✕That unflagged conversations are safe - a missing signal means "not detected," never "cleared."
- ✕Anything outside the submitted text - no photos, profiles, or account metadata are analyzed.
Boundary: Dating Safety signals flag risk language in a message - they do not determine that a user is a scammer, and a clean result is not clearance. Enforcement stays with your moderation team.
Access the taxonomy through the API
Check Dating Safety availability and endpoint programmatically via the public catalog endpoint - no authentication required. Include your API key to also retrieve taxonomy size and supported languages.
curl -X GET https://sentiqra.tech/v1/meta/domains/dating-safety \
-H "Authorization: Bearer sq_live_your_key_here"Example response (authenticated):
{
"catalog_version": "...",
"domain": {
"id": "dating_safety",
"name": "Dating Safety",
"status": "production",
"taxonomy": { "groups": 5, "detection_labels": 200 },
"languages": [ ... ]
}
}Signals returned by the analyzers use code for the category or label slug - these correspond to the categories and indicators documented on this page.