Jove
Visualize
Contáctanos
JoVE
x logofacebook logolinkedin logoyoutube logo
ACERCA DE JoVE
Visión GeneralLiderazgoBlogCentro de Ayuda JoVE
AUTORES
Proceso de PublicaciónConsejo EditorialAlcance y PolíticasRevisión por ParesPreguntas FrecuentesEnviar
BIBLIOTECARIOS
TestimoniosSuscripcionesAccesoRecursosConsejo Asesor de BibliotecasPreguntas Frecuentes
INVESTIGACIÓN
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchivo
EDUCACIÓN
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualCentro de Recursos para ProfesoresSitio de Profesores
Términos y Condiciones de Uso
Política de Privacidad
Políticas

Videos de Conceptos Relacionados

Stereotype Content Model02:16

Stereotype Content Model

The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence categorization, a person will feel...
Natural and Artificial Concepts01:24

Natural and Artificial Concepts

In psychology, concepts can be divided into two categories: natural and artificial. Natural concepts are formed through direct or indirect experiences. For example, consider the concept of snow. If you live in a place with regular snowfall, such as Essex Junction, Vermont, you know snow through direct experiences. You’ve seen it fall, touched it, shoveled it, and played in it. You recognize its texture, appearance, and even its smell. In contrast, if you live on an island like Saint Vincent in...
Components of Language01:24

Components of Language

Language, whether spoken, signed, or written, consists of specific components: lexicon and grammar. The lexicon is the vocabulary of a language, comprising its words. Grammar is the set of rules used to convey meaning through the lexicon. For example, English grammar adds “-ed” to most verbs to indicate past tense. Words are formed by combining phonemes, which are the basic sound units of a language. Different languages have different sets of phonemes (e.g., “ah” vs. “eh”). Phonemes combine to...
Language Development01:22

Language Development

Children master language quickly and with relative ease, supported by both biological predisposition and reinforcement. B. F. Skinner (1957) proposed that language is learned through reinforcement, while Noam Chomsky (1965) argued that language acquisition mechanisms are biologically determined.
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...
Language and Cognition01:27

Language and Cognition

Language serves as a bridge between ideas and communication, influencing how individuals perceive and interact with the world. Psychologists have long debated whether language shapes thought or vice versa. This discussion gained grip with Edward Sapir and Benjamin Lee Whorf in the 1940s, who proposed that language determines thought, a concept known as linguistic determinism. They suggested that the vocabulary and structure of a language influence how its speakers think and perceive reality.
Automatic Processing and Automatic Social Behavior01:28

Automatic Processing and Automatic Social Behavior

Automatic processing refers to the cognitive operations that occur without conscious intent or awareness, playing a fundamental role in shaping social cognition and behavior. These processes enable individuals to navigate complex social environments efficiently by relying on mental shortcuts and pre-existing knowledge structures known as schemas. One of the most influential mechanisms underlying automatic processing is priming, which subtly activates mental representations through exposure to...

También podría leer

Artículos Relacionados

Artículos vinculados a este trabajo por autores compartidos, revista y gráfico de citas.

Ordenar por
Same author

Directionality and representativeness are differentiable components of stereotypes in large language models.

PNAS nexus·2024
Same author

ChatGPT as Research Scientist: Probing GPT's capabilities as a Research Librarian, Research Ethicist, Data Generator, and Data Predictor.

Proceedings of the National Academy of Sciences of the United States of America·2024
Same author

REFORMS: Consensus-based Recommendations for Machine-learning-based Science.

Science advances·2024
Same author

Extracting intersectional stereotypes from embeddings: Developing and validating the Flexible Intersectional Stereotype Extraction procedure.

PNAS nexus·2024
Same author

Polarization under rising inequality and economic decline.

Science advances·2020

Video Experimental Relacionado

Updated: Jun 14, 2026

Experimental Paradigm for Measuring the Effect of Induced Emotion on Grammar Learning
05:33

Experimental Paradigm for Measuring the Effect of Induced Emotion on Grammar Learning

Published on: January 29, 2020

La semántica derivada automáticamente de los corpus de lenguaje contiene sesgos similares a los humanos

Aylin Caliskan1, Joanna J Bryson1,2, Arvind Narayanan1

  • 1Center for Information Technology Policy, Princeton University, Princeton, NJ, USA. aylinc@princeton.edu jjb@alum.mit.edu arvindn@cs.princeton.edu.

Science (New York, N.Y.)
|April 15, 2017
PubMed
Resumen
Este resumen es generado por máquina.

Los modelos de aprendizaje automático entrenados en texto web replican los sesgos semánticos humanos que se encuentran en las pruebas de asociación implícita. Esto revela cómo los sesgos históricos están incrustados en los datos lingüísticos, ofreciendo métodos para identificar y abordar los sesgos culturales en la tecnología.

Más Videos Relacionados

Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

Videos de Experimentos Relacionados

Last Updated: Jun 14, 2026

Experimental Paradigm for Measuring the Effect of Induced Emotion on Grammar Learning
05:33

Experimental Paradigm for Measuring the Effect of Induced Emotion on Grammar Learning

Published on: January 29, 2020

Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

Área de la Ciencia:

  • Inteligencia artificial
  • Procesamiento del lenguaje natural
  • Ciencias sociales computacionales

Sus antecedentes:

  • El aprendizaje automático (ML) deriva la inteligencia artificial mediante la identificación de patrones en los datos.
  • Los cuerpos del lenguaje humano contienen sesgos sociales implícitos.
  • La prueba de asociación implícita (IAT) mide la fuerza de las asociaciones automáticas entre conceptos.

Objetivo del estudio:

  • Investigar si los modelos de aprendizaje automático entrenados en el lenguaje humano exhiben sesgos semánticos similares a los humanos.
  • Determinar si los modelos ML pueden replicar los sesgos medidos por el IAT.
  • Explorar el potencial del aprendizaje automático para identificar y mitigar los sesgos culturales.

Principales métodos:

  • Aplicó un modelo estadístico de aprendizaje automático a un gran corpus de texto de la World Wide Web.
  • Entrenó el modelo con datos de texto estándar.
  • Se evaluaron las asociaciones semánticas del modelo frente a los sesgos humanos conocidos, incluidos los medidos por el IAT.

Principales resultados:

  • El modelo ML replicó un espectro de sesgos semánticos humanos, reflejando los resultados de IAT.
  • Se observaron sesgos en varios dominios, incluidos los moralmente neutrales (insectos, flores), problemáticos (raza, género) y verídicos (género y carreras / nombres).
  • Los corpora de texto imprimen con precisión los sesgos humanos históricos, que se pueden recuperar a través del análisis de ML.

Conclusiones:

  • Los modelos de aprendizaje automático entrenados en datos de texto del mundo real heredan y reflejan sesgos semánticos humanos.
  • Los datos de texto sirven como un repositorio de sesgos históricos, que se pueden cuantificar utilizando ML.
  • Los métodos desarrollados ofrecen un enfoque prometedor para detectar y abordar los sesgos culturales y tecnológicos.