An experimental study for the Cross Domain Author Profiling classification

Author Profiling is the task of predicting characteristics of the author of a text, such as age, gender, personality, native language, etc. This is a task of growing importance due to the potential applications in security, crime detection and marketing, among others. An interesting point is to stud...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Garciarena Ucelay, María José, Villegas, María Paula, Cagnina, Leticia, Errecalde, Marcelo Luis
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2015
Materias:
Ciencias Informáticas
Natural Language Processing
cross domain classification
author profiling
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/50445
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-50445
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Natural Language Processing
cross domain classification
author profiling
spellingShingle Ciencias Informáticas
Natural Language Processing
cross domain classification
author profiling
Garciarena Ucelay, María José
Villegas, María Paula
Cagnina, Leticia
Errecalde, Marcelo Luis
An experimental study for the Cross Domain Author Profiling classification
topic_facet Ciencias Informáticas
Natural Language Processing
cross domain classification
author profiling
description Author Profiling is the task of predicting characteristics of the author of a text, such as age, gender, personality, native language, etc. This is a task of growing importance due to the potential applications in security, crime detection and marketing, among others. An interesting point is to study the robustness of a classifier when it is trained with a dataset and tested with others containing different characteristics. Commonly this is called cross domain experimentation. Although different cross domain studies have been done for datasets in English language, for Spanish it has recently begun. In this context, this work presents a study of cross domain classification for the author profiling task in Spanish. The experimental results showed that using corpora with different levels of formality we can obtain robust classifiers for the author profiling task in Spanish language.
format Objeto de conferencia
Objeto de conferencia
author Garciarena Ucelay, María José
Villegas, María Paula
Cagnina, Leticia
Errecalde, Marcelo Luis
author_facet Garciarena Ucelay, María José
Villegas, María Paula
Cagnina, Leticia
Errecalde, Marcelo Luis
author_sort Garciarena Ucelay, María José
title An experimental study for the Cross Domain Author Profiling classification
title_short An experimental study for the Cross Domain Author Profiling classification
title_full An experimental study for the Cross Domain Author Profiling classification
title_fullStr An experimental study for the Cross Domain Author Profiling classification
title_full_unstemmed An experimental study for the Cross Domain Author Profiling classification
title_sort experimental study for the cross domain author profiling classification
publishDate 2015
url http://sedici.unlp.edu.ar/handle/10915/50445
work_keys_str_mv AT garciarenaucelaymariajose anexperimentalstudyforthecrossdomainauthorprofilingclassification
AT villegasmariapaula anexperimentalstudyforthecrossdomainauthorprofilingclassification
AT cagninaleticia anexperimentalstudyforthecrossdomainauthorprofilingclassification
AT errecaldemarceloluis anexperimentalstudyforthecrossdomainauthorprofilingclassification
AT garciarenaucelaymariajose experimentalstudyforthecrossdomainauthorprofilingclassification
AT villegasmariapaula experimentalstudyforthecrossdomainauthorprofilingclassification
AT cagninaleticia experimentalstudyforthecrossdomainauthorprofilingclassification
AT errecaldemarceloluis experimentalstudyforthecrossdomainauthorprofilingclassification
bdutipo_str Repositorios
_version_ 1764820475046789122

Ejemplares similares