Predicting elections for multiple countries using Twitter and polls

Tsakalidis, Adam; Papadopoulos, S.; Cristea, A.I.; Kompatsiaris, Yiannis

doi:10.1109/mis.2015.17

Predicting elections for multiple countries using Twitter and polls

Tsakalidis, Adam; Papadopoulos, S.; Cristea, A.I.; Kompatsiaris, Yiannis

Authors

Adam Tsakalidis

S. Papadopoulos

Professor Alexandra Cristea alexandra.i.cristea@durham.ac.uk
Professor

Yiannis Kompatsiaris

Abstract

The authors' work focuses on predicting the 2014 European Union elections in three different countries using Twitter and polls. Past works in this domain relying strictly on Twitter data have been proven ineffective. Others, using polls as their ground truth, have raised questions regarding the contribution of Twitter data for this task. Here, the authors treat this task as a multivariate time-series forecast, extracting Twitter- and poll-based features and training different predictive algorithms. They've achieved better results than several past works and the commercial baseline.

Citation

Tsakalidis, A., Papadopoulos, S., Cristea, A., & Kompatsiaris, Y. (2015). Predicting elections for multiple countries using Twitter and polls. IEEE Intelligent Systems, 30(2), 10-17. https://doi.org/10.1109/mis.2015.17

Journal Article Type	Article
Acceptance Date	Jan 5, 2015
Online Publication Date	Jan 26, 2015
Publication Date	Mar 1, 2015
Deposit Date	Jul 11, 2018
Publicly Available Date	Jul 31, 2018
Journal	IEEE Intelligent Systems
Print ISSN	1541-1672
Publisher	Institute of Electrical and Electronics Engineers
Peer Reviewed	Peer Reviewed
Volume	30
Issue	2
Pages	10-17
DOI	https://doi.org/10.1109/mis.2015.17
Related Public URLs	http://wrap.warwick.ac.uk/75812/

Files

Accepted Journal Article (644 Kb)
PDF

Copyright Statement
© 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.