SciELO - Scientific Electronic Library Online

vol.38 número59La relación interpersonal con la audiencia: El caso del discurso del presidente venezolano Hugo ChávezSobre los efectos de combinar Análisis Semántico Latente con otras técnicas de procesamiento de lenguaje natural para la evaluación de preguntas abiertas índice de autoresíndice de materiabúsqueda de artículos
Home Pagelista alfabética de revistas  

Servicios Personalizados




Links relacionados


Revista signos

versión On-line ISSN 0718-0934


GUTIERREZ, Rosa María. Latent Semantic Analysis: A psychological theory of the meaning? . Rev. signos [online]. 2005, vol.38, n.59, pp.303-323. ISSN 0718-0934.

LSA, Latent Semantic Analysis, is a type of computational analysis based on a mathematical algorithm that helps to determine and quantify the similarity of meaning among pieces of texts whose field of knowledge is the same. Due to its functionality, LSA has been considered a psychological theory of meaning (Kintsch, 2002), able to emulate and explain how human beings learn, determine and use the meaning of words (Landauer & Dumais, 1997) and knowledge in general (Landauer, Foltz & Laham, 1998). Arguing in favor or against LSA, beyond the classical debate over whether a mechanism not endowed with conscience can indeed respond to such complex issues (Perfetti, 1998), means getting to know and understanding what the LSA working system is. This is the main reason to present a brief description of the LSA system, starting from its mathematical basis, the relationship between its basis and its underlying semantic assumptions, and two applications developed for the study of cognitive processes. Essentially, the article covers a revision and bibliographical discussion aimed at compiling information found in other sources to disseminate it in Spanish with the purpose of questioning and discussing the semantic nature ascribed to this analysis from a linguistic perspective.

Palabras clave : Latent Semantic Analysis; psychological theory of meaning; latent similarity.

        · resumen en Español     · texto en Español


Creative Commons License Todo el contenido de esta revista, excepto dónde está identificado, está bajo una Licencia Creative Commons