DISCRIMINATION GROUPS REFERENCE
Discrimination Analysis Discrimination Groups
Discrimination Analysis organizes detection into 6 discrimination groups covering 200 indicators across 16 languages.
All Discrimination Groups
Each discrimination 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
Conduct Bias
conduct_bias
40
40 signals - request access
for the complete list.
View 40 indicators
Conduct Bias
conduct_bias
The complete signal list is available to customers. Request access to view it.
02
Identity Origin
identity_origin
30
30 signals - request access
for the complete list.
View 30 indicators
Identity Origin
identity_origin
The complete signal list is available to customers. Request access to view it.
03
Identity Status
identity_status
40
40 signals - request access
for the complete list.
View 40 indicators
Identity Status
identity_status
The complete signal list is available to customers. Request access to view it.
04
Identity Personal
identity_personal
30
30 signals - request access
for the complete list.
View 30 indicators
Identity Personal
identity_personal
The complete signal list is available to customers. Request access to view it.
05
Context Access
context_access
40
40 signals - request access
for the complete list.
View 40 indicators
Context Access
context_access
The complete signal list is available to customers. Request access to view it.
06
Conduct Hostile
conduct_hostile
20
20 signals - request access
for the complete list.
View 20 indicators
Conduct Hostile
conduct_hostile
The complete signal list is available to customers. Request access to view it.
Reading Discrimination Analysis output
What you can safely infer from a result - and what you must not.
Intended task
Flag documented exclusionary and discriminatory language patterns tied to protected classes - for human or policy review.
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"discrimination"; 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. - Sees only the submitted text - the writer's identity, role, and the document's legal context are not inputs.
Ordinary positive
“Applicants must be under 40 and born in this country - no exceptions.”
Safe inference: The text matches documented exclusion patterns on two protected classes. Route it to review with the labels attached.
Confusing negative · Quotation
“The handbook's old rule - "applicants must be born in this country" - was struck down in 2019.”
What happens: The exclusion pattern can still match the quoted clause. Signals flag the language for review - they do not read the surrounding context that makes this a compliance document describing a repealed rule.
Why it's tricky: Audits, legal analysis, and journalism all quote discriminatory language. Ambiguous phrasing ("we need someone young and energetic") may produce weak or no signals - absence is "not detected," never clearance. Both cases are why flagged text goes to review, not to automatic verdicts.
What you can safely infer
- Which documented protected-class patterns the text matched, and at what strength.
- That the result is reproducible - the receipt ties the labels to the configuration that produced them.
What you must not infer
- ✕That unlawful discrimination occurred - legality is a determination for your counsel and jurisdiction.
- ✕The author's intent, or that a specific person was harmed.
- ✕That clean text contains no exclusionary content - a missing signal is "not detected," never "compliant."
Boundary: Discrimination signals flag exclusionary language for review - they do not determine that unlawful discrimination occurred, and they say nothing about intent.
Access the taxonomy through the API
Check Discrimination Analysis 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/discrimination \
-H "Authorization: Bearer sq_live_your_key_here"Example response (authenticated):
{
"catalog_version": "...",
"domain": {
"id": "discrimination",
"name": "Discrimination Analysis",
"status": "production",
"taxonomy": { "groups": 6, "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.