Skip to main content

Behavioral Attributes

Ferretly uses machine learning to analyze posts and images for specific types of behaviors. When you run a background check, Ferretly retrieves posts from your subject's social media profiles. Each post and image is then analyzed for 11 different behavioral attributes and a custom set of keywords.

If a post exceeds a certain threshold confidence for at least one behavior Ferretly flags it. For example, a post might have a 65% confidence of Disparaging language and a 73% confidence of Prejudice. In such cases, the flag will indicate Prejudice as the behavioral attribute. It's also possible for a post and its associated image to be flagged simultaneously. In this case, the flag will indicate both the reason for the post text and the image triggering one of the behavioral attributes.

Below is a table that lists the behavioral attributes surfaced by Ferretly and their corresponding definitions.

Behavior

Definition

Disparaging

Name calling or derogatory statements toward an individual about their physical characteristics such as weight, height, looks, intelligence, etc.

Drug/Alcohol Mention

Statements related to drugs and/or drug use including slang words, street names and phrases.

Drug Image

Images of pills, syringes, paraphernalia. It may include smoking, drinking, and injections.

Gory Image

Images of disfigurations, open wounds, burns, and crime scenes.

Nudity Image

Images of explicit and non-explicit nudity, adult content, and pornographic content.

Prejudice

Derogatory, abusive and/or threatening statements toward a specific group of people typically on the basis of race, religion or sexual orientation.

Politics/Government

Statements focused on government policies, actions or specific politicians or ideologies. These often focus on specific issues such as abortion, environmental, immigration, government regulations, etc.

Profanity

Obscene language, cursing, swearing or in general crude or vulgar words and phrases

Self-Harm

Indications of wanting to hurt oneself or take one's own life intentionally. This could also be mentions of suicide or suicidal behavior in others.

Suggestive

Includes expressions relating to sexual misconduct that could be considered sexually demeaning or sexual harassment.

Threats

An intent to inflict harm or loss of another person’s life.

Keywords

Flags posts based on matches to custom keywords provided.