Interface HateSpeechResult

interface HateSpeechResult {
    classification: HateSpeechClass;
    confidence: number;
    score: number;
    severity: SafetySeverity;
    targetGroups: string[];
    violations: SafetyViolation[];
}

Index

Properties

classification confidence score severity targetGroups violations

Properties

classification

classification: HateSpeechClass

Primary classification

confidence

confidence: number

Confidence in the classification (0-1)

score

score: number

Overall hate speech score (0-1)

severity

severity: SafetySeverity

Severity classification

targetGroups

targetGroups: string[]

Target groups identified

violations

violations: SafetyViolation[]

Individual violations