English español

Repositorio de la Universidad de Oviedo. > Producción Bibliográfica de UniOvi: RECOPILA > Artículos >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10651/11452

Title: Don't turn social media into another 'literary digest' poll
Author(s): Gayo Avello, Daniel
Issue date: 2011
Publisher: ACM
Publisher version: http://dx.doi.org/10.1145/2001269.2001297
Citation: Communications of the ACM, 54(10), p. 121-128 (2011); doi:10.1145/2001269.2001297
Format extent: p. 121-128
Abstract: 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
Local identifier: 20110941
Appears in Collections:Artículos

Files in This Item:

File SizeFormat
Social-Media-Literary-Digest-authors.pdf283,75 kBAdobe PDFView/Open

Exportar a Mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.


Base de Datos de Autoridades Biblioteca Universitaria Consultas / Sugerencias