RepositoryWebrefDetailedEntityScores

AI Overview😉

The potential purpose of this module is to analyze the relevance and importance of entities (e.g. people, organizations, locations) within a document or webpage. It assigns scores to these entities based on their connectedness to other entities, their topicality, and other factors, to determine their significance in the context of the document.
This module could impact search results by influencing the ranking of documents based on the relevance and importance of the entities they contain. Documents that contain entities with high topicality scores, for example, may be considered more relevant to a user's search query and therefore rank higher in search results.
To be more favorable to this module, a website could focus on creating high-quality, entity-rich content that clearly establishes the relationships between entities. This could involve using schema.org markup to identify and describe entities, as well as creating content that is well-structured and easy to understand. Additionally, websites could focus on establishing a clear authorship and publication hierarchy, as the module appears to take into account the author and publisher of a document when assigning entity scores.

Interesting Module? Vote 👇

Voting helps other researchers find interesting modules.

Current Votes: 0

GoogleApi.ContentWarehouse.V1.Model.RepositoryWebrefDetailedEntityScores (google_api_content_warehouse v0.4.0)

Detailed scores about the topicality of an entity. Next available tag: 17

Attributes

connectedness (type: number(), default: nil) - Represents how much the entity is connected/related to the other entities in the document. This signal partially influences the topicality score, but it is not totally aligned with it: an entity can be very related to the rest of the document, but not central for understanding it. Likewise, an entity can be central to understand a document, but not very related to the rest of the document. The value is in [0, 1].
docScore (type: number(), default: nil) - How well the document scores for the entity. The score is unnormalized, and serves as a relative ranking signal between different documents for an entity.
isAuthor (type: boolean(), default: nil) - True if the entity is the author of the document. This was mainly developed and tuned for news articles (e.g. /m/02x27qn on "www.vogue.com/article/flint-town-netflix") but is also popluated for other content (e.g. scientific articles). Important: the semantics of this field may change in the future or it might be removed and replaced with a different API. If you want to use this field, please reach out to ke-authors@ first.
isPublisher (type: boolean(), default: nil) - True if the entity is the publisher of the page (e.g. CNN on "http://www.cnn.com/foo/bar").
isReferencePage (type: boolean(), default: nil) - Set to true iff the entity matches the full URL of the document, meaning that it is a reference page or related page of the entity.
normalizedTopicality (type: number(), default: nil) - Representation of the topicality score that is normalized in [0, 1] and which sum over all entities in the document is 1. It represents the "proportion" of the document that talks about the entity. This score is less human interpretable as the bucketized topicality score (EntityAnnotations.topicality_score), but is more suited for some usages like aggregations.
profileUrl (type: String.t, default: nil) - Contains the link to the author's profile url on the platform.
referencePageScores (type: GoogleApi.ContentWarehouse.V1.Model.RepositoryWebrefReferencePageScores.t, default: nil) - Signals used for mining new reference pages, set by the reference-page-scorer processor (that is turned off by default). This field is not populated, except for special reference page extraction runs.
relevanceScore (type: number(), default: nil) - Relevance score generated by a Machine Learning entity classifier. This signal is similar to topicality, but machine learning based and supported by EntitySignals, not Webref. See http://go/entityclassifier for details on the classifier.

Summary

Types

t()

Functions

decode(value, options)

Unwrap a decoded JSON object into its complex fields.

Types

Link to this type

t()

@type t() ::
  %GoogleApi.ContentWarehouse.V1.Model.RepositoryWebrefDetailedEntityScores{
    connectedness: number() | nil,
    docScore: number() | nil,
    isAuthor: boolean() | nil,
    isPublisher: boolean() | nil,
    isReferencePage: boolean() | nil,
    normalizedTopicality: number() | nil,
    profileUrl: String.t() | nil,
    referencePageScores:
      GoogleApi.ContentWarehouse.V1.Model.RepositoryWebrefReferencePageScores.t()
      | nil,
    relevanceScore: number() | nil
  }

Functions

Link to this function

decode(value, options)

@spec decode(struct(), keyword()) :: struct()

Unwrap a decoded JSON object into its complex fields.