Loading...
Please wait, while we are loading the content...
Similar Documents
Estudio de los rasgos lingüísticos de la mentira en el medio escrito: un análisis contrastivo inglés-español
| Content Provider | Semantic Scholar |
|---|---|
| Author | Sánchez-Lafuente, Ángela Almela |
| Copyright Year | 2012 |
| Abstract | espanolEl objetivo principal de esta tesis doctoral es el analisis de las caracteristicas linguisticas de la mentira en el lenguaje escrito en ingles y en espanol, para lo cual se ha llevado a cabo un analisis contrastivo entre ambas lenguas. Se han realizado diversos experimentos de clasificacion automatica sobre dos corpora ad-hoc para testar la clasificacion de los textos segun su valor de verdad. En el primer experimento se han aplicado tecnicas de aprendizaje automatico y se han comparado los resultados con un modelo Bag-of-Words, obteniendo una tasa de exito maxima de 78,5% para ingles y de 84,5% para espanol. El segundo experimento ha incluido dos tecnicas estadisticas: analisis discriminante y regresion logistica binaria, siendo los resultados de clasificacion igualmente satisfactorios. Ademas de ello, se ha confirmado el papel fundamental en la configuracion de la mentira escrita de parametros tales como la longitud del texto, referencias propias, entendimiento y exclusiones. Palabras clave: linguistica computacional, deteccion de la mentira, analisis contrastivo, clasificacion automatica. EnglishThe main aim of this PhD thesis is to analyse the linguistic cues to deception in written language both in English and Spanish, performing a contrastive analysis between both languages. For this purpose, several automatic classification experiments have been performed on two ad-hoc corpora in both languages, in order to check whether the texts could be successfully classified on the basis of their truth value. In the first set of experiments, a machine learning technique has been applied on the data and compared to a Bag-of-Words model, obtaining a maximum rate of 78.5% for English and 84.5% for Spanish. The second experiment involved statistical techniques, namely discriminant function analysis and binary logistic regression, and the results obtained proved remarkably successful too. In addition, they confirm the leading role in deception detection of parameters such as text length, self-references, insight and exclusive words. Keywords: computational linguistics, deception detection, contrastive analysis, automatic classification. |
| Starting Page | 1 |
| Ending Page | 1 |
| Page Count | 1 |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | https://digitum.um.es/xmlui/bitstream/10201/29889/1/TESIS_def.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
