Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.
Excerpt

Verity scans and analyzes page analysis involves scanning and analyzing both text and prominent imagery on a web page and . Verity returns a JSON response with IAB Contextual Categories page analysis response that includes contextual categories (IAB v1.0 and , IAB v2.0 and Event targeting categories. For brand safety, Verity classifies unsafe content into and Events), keywords, sentiment evaluation, and brand safety scoring. The brand safety scoring includes an overall Safe/Unsafe flag, plus classifications for multiple threat categories defined by GumGum , (including drugs, weapons, and sexual content. The response also includes keyword and sentiment evaluation data.

...

).

Verity page analysis works by extracting metadata and significant content from a page, then applying computer vision (CV) and natural language processing (NLP) to the extracted data.

Note: Verity does not download or analyze the CSS, JavaScript, navigation, footer, sidebars, third-party ads, user-generated content, or other areas extraneous to the main textual content of the page. 

The Verity page analysis response is aggregated into the following Verity page classification report sections:

  • IAB Categories
    Identifies and scores contextual targeting categories. Includes standard IAB v1.0 and IAB v2.0 categories.

  • Keywords
    Extracts and scores page keywords according to prominence.

  • Brand Safety
    Identifies and scores brand safety threats according to GumGum's Threat classification taxonomy, in compliance with The 4A’s Advertising Assurance Brand Safety Floor

  • Event Categories 
    Identifies Events according to GumGum's Event classification taxonomy. There are Event categories for major seasonal events such as holidays or the sporting events.

  • Sentiments  
    Analyzes the overall opinions expressed within the content of a page, and classifies the percentage of positive, negative, and neutral sentiments.

Verity page analysis works by extracting metadata and significant content from a page, then applying computer vision (CV) and natural language processing (NLP) to the extracted data.

...

  • .

...

Page Analysis Categories and Keywords

Verity page analysis includes combined text and image classifications, and the top keywords detected on the pageThe following table summarizes the classifications and keywords that are detected during page analysis.

Brand Safety (Threat) Categories 

Contextual
Categories

Keywords

Violence
Illegal
Drugs
Sexual
Obscene
Hate
Disaster
Malware
Illness

IAB v1.0
372 categories

IAB v2.0
698 categories

Events  
~150 categories

Sentiment  
Positive, Neutral, Negative categories

Contextual targeting keywords
Named Entities  

Page Analysis Language Support

Verity classification categories and keywords and categories  are supported in the languages as specified in the following table.:

Language

Keywords

Categories

Threat

IAB V2

IAB V1

Event

Sentiment

English

Japanese




Verity Response Format

The Verity API response format is JavaScript Object Notation (JSON)  Content-Type: application/json; charset=UTF-8.

...