Entity extraction analysis

Entity extraction analysis is the process of extracting named entities from unstructured text such as press articles, Facebook posts, or tweets, and categorizing them. Typically, a named entity is a proper noun that falls into a commonly understood category such as a person, organization, or location.

You can perform the following types of entity extraction analysis:

• Identify topics and their synonyms in the analyzed text. You can configure the entity extraction analysis to identify the terms or keywords that you specified in the Text Analyzer rule form as Topics. You can assign a set of synonyms to each topic because the topic can be referred to in multiple ways, depending on the domain.
• Identify entities that belong to the following predefined categories (Data, Date, Location, Organization, Person, and Product). The identification of the entity and the category to which it belongs is based on the entity extraction models available in Pega Platform.
• Create your own entities and import them into Pega Platform entity extraction rules. Each entity extraction rule is a decision data record that contains a Rule-based Text Annotation (Ruta) script that enables the extraction of a particular entity. Use entity extraction rules to extract entities whose structures match a specific pattern or for entities that belong to a specific dictionary.

Open topic with navigation