Investigating verbal intelligence using the TF-IDF approach

Zablotskaya, Kseniya; Fernández Martínez, Fernando y Minker, Wolfgang (2012). Investigating verbal intelligence using the TF-IDF approach. En: "LREC 2012, Eighth International Conference on Language Resources and Evaluation", 21/05/2012 - 27/05/2013, Istanbul. ISBN 978-2-9517408-7-7. pp. 1573-1576.

Descripción

Título: Investigating verbal intelligence using the TF-IDF approach
Autor/es:
  • Zablotskaya, Kseniya
  • Fernández Martínez, Fernando
  • Minker, Wolfgang
Tipo de Documento: Ponencia en Congreso o Jornada (Artículo)
Título del Evento: LREC 2012, Eighth International Conference on Language Resources and Evaluation
Fechas del Evento: 21/05/2012 - 27/05/2013
Lugar del Evento: Istanbul
Título del Libro: Proceedings of LREC 2012, Eighth International Conference on Language Resources and Evaluation
Fecha: Mayo 2012
ISBN: 978-2-9517408-7-7
Materias:
Palabras Clave Informales: Verbal intelligence, cosine similarity, TF-IDF measures
Escuela: E.T.S.I. Telecomunicación (UPM)
Departamento: Ingeniería Electrónica
Licencias Creative Commons: Reconocimiento - Sin obra derivada - No comercial

Texto completo

[img]
Vista Previa
PDF (Document Portable Format) - Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (482kB) | Vista Previa

Resumen

In this paper we investigated differences in language use of speakers yielding different verbal intelligence when they describe the same event. The work is based on a corpus containing descriptions of a short film and verbal intelligence scores of the speakers. For analyzing the monologues and the film transcript, the number of reused words, lemmas, n-grams, cosine similarity and other features were calculated and compared to each other for different verbal intelligence groups. The results showed that the similarity of monologues of higher verbal intelligence speakers was greater than of lower and average verbal intelligence participants. A possible explanation of this phenomenon is that candidates yielding higher verbal intelligence have a better short-term memory. In this paper we also checked a hypothesis that differences in vocabulary of speakers yielding different verbal intelligence are sufficient enough for good classification results. For proving this hypothesis, the Nearest Neighbor classifier was trained using TF-IDF vocabulary measures. The maximum achieved accuracy was 92.86%.

Más información

ID de Registro: 20424
Identificador DC: http://oa.upm.es/20424/
Identificador OAI: oai:oa.upm.es:20424
URL Oficial: http://www.lrec-conf.org/proceedings/lrec2012/pdf/352_Paper.pdf
Depositado por: Memoria Investigacion
Depositado el: 05 Oct 2013 10:42
Ultima Modificación: 21 Abr 2016 23:13
  • Open Access
  • Open Access
  • Sherpa-Romeo
    Compruebe si la revista anglosajona en la que ha publicado un artículo permite también su publicación en abierto.
  • Dulcinea
    Compruebe si la revista española en la que ha publicado un artículo permite también su publicación en abierto.
  • Recolecta
  • e-ciencia
  • Observatorio I+D+i UPM
  • OpenCourseWare UPM