How should Verity Threat confidence levels be interpreted?

Verity analyzes content for threat categories. If a threat category is detected, the threat category is listed in the analysis results along with a confidence level.

Threat risk levels are:

VERY_HIGH
HIGH
MODERATE
LOW
VERY_LOW

For example:

"threats": [
{
    "id": "GGT6",
    "category": "Hate speech, harassment, and cyberbullying",
    "confidence": "VERY_HIGH"
  },

  {
    "id": "GGT1",
    "category": "Violence and gore",
    "confidence": "HIGH",
"risk": “HIGH”
  }
]

Clients can use these “confidence” levels when assigning thresholds for risk tolerance, as discussed in What are Verity’s brand safety capabilities?

Note that the confidence levels represent the risk potential of unsafe content within a page, video, image, or text string.

In traditional statistical measures, confidence in observed results may be assessed according to the number of samples involved in a test. Larger scale sampling leads to a higher confidence score. However, Verity confidence levels are not related to the quantity of sample data.

The goal of Verity threat levels is to determine whether it is safe to display ads on a given page or video. For example, a result “confidence”: “VERY_LOW” should be interpreted as Verity identifying a very low risk for that category within the content, with a high level of confidence.