RUO Principal

Repositorio Institucional de la Universidad de Oviedo

Ver ítem 
  •   RUO Principal
  • Producción Bibliográfica de UniOvi: RECOPILA
  • Artículos
  • Ver ítem
  •   RUO Principal
  • Producción Bibliográfica de UniOvi: RECOPILA
  • Artículos
  • Ver ítem
    • español
    • English
JavaScript is disabled for your browser. Some features of this site may not work without it.

Listar

Todo RUOComunidades y ColeccionesPor fecha de publicaciónAutoresTítulosMateriasxmlui.ArtifactBrowser.Navigation.browse_issnPerfil de autorEsta colecciónPor fecha de publicaciónAutoresTítulosMateriasxmlui.ArtifactBrowser.Navigation.browse_issn

Mi cuenta

AccederRegistro

Estadísticas

Ver Estadísticas de uso

AÑADIDO RECIENTEMENTE

Novedades
Repositorio
Cómo publicar
Recursos
FAQs

Don't turn social media into another 'literary digest' poll

Autor(es) y otros:
Gayo Avello, DanielAutoridad Uniovi
Fecha de publicación:
2011
Editorial:

ACM

Versión del editor:
http://dx.doi.org/10.1145/2001269.2001297
Citación:
Communications of the ACM, 54(10), p. 121-128 (2011); doi:10.1145/2001269.2001297
Descripción física:
p. 121-128
Resumen:

User generated content has experienced an explosive growth both in the diversity of applications and the volume of topics covered by its users. Content published in micro-blogging systems like Twitter is thought to be feasibly data-mined in order to take the pulse of society. Recently, a number of positive studies have been published praising the goodness of relatively simple approaches to sampling, opinion mining, and sentiment analysis. This paper will attempt to play devil's advocate by detailing a study in which such simple approaches largely overestimated Obama's victory in the 2008 U.S. Presidential Elections. A thorough post-mortem of that experiment has been conducted and several important lessons have been extracte

User generated content has experienced an explosive growth both in the diversity of applications and the volume of topics covered by its users. Content published in micro-blogging systems like Twitter is thought to be feasibly data-mined in order to take the pulse of society. Recently, a number of positive studies have been published praising the goodness of relatively simple approaches to sampling, opinion mining, and sentiment analysis. This paper will attempt to play devil's advocate by detailing a study in which such simple approaches largely overestimated Obama's victory in the 2008 U.S. Presidential Elections. A thorough post-mortem of that experiment has been conducted and several important lessons have been extracte

URI:
http://hdl.handle.net/10651/11452
ISSN:
0001-0782
Identificador local:

20110941

DOI:
10.1145/2001269.2001297
Colecciones
  • Artículos [37532]
  • Informática [872]
Ficheros en el ítem
Thumbnail
untranslated
Social-Media-Literary-Digest-authors.pdf (283.7Kb)
Métricas
Compartir
Exportar a Mendeley
Estadísticas de uso
Estadísticas de uso
Metadatos
Mostrar el registro completo del ítem
Página principal Uniovi

Biblioteca

Contacto

Facebook Universidad de OviedoTwitter Universidad de Oviedo
El contenido del Repositorio, a menos que se indique lo contrario, está protegido con una licencia Creative Commons: Attribution-NonCommercial-NoDerivatives 4.0 Internacional
Creative Commons Image