Predicting the Brexit Vote by Tracking and Classifying Public Opinion Using Twitter Data. / Amador, Julio; Collignon, Sofia; Benoit, Kenneth; Akitaka, Matsuo.

In: Statistics, Politics and Policy, Vol. 8, No. 1, 26.10.2017, p. 85-104.

Research output: Contribution to journalArticle

Published

Standard

Predicting the Brexit Vote by Tracking and Classifying Public Opinion Using Twitter Data. / Amador, Julio; Collignon, Sofia; Benoit, Kenneth; Akitaka, Matsuo.

In: Statistics, Politics and Policy, Vol. 8, No. 1, 26.10.2017, p. 85-104.

Research output: Contribution to journalArticle

Harvard

Amador, J, Collignon, S, Benoit, K & Akitaka, M 2017, 'Predicting the Brexit Vote by Tracking and Classifying Public Opinion Using Twitter Data', Statistics, Politics and Policy, vol. 8, no. 1, pp. 85-104. https://doi.org/10.1515/spp-2017-0006

APA

Amador, J., Collignon, S., Benoit, K., & Akitaka, M. (2017). Predicting the Brexit Vote by Tracking and Classifying Public Opinion Using Twitter Data. Statistics, Politics and Policy, 8(1), 85-104. https://doi.org/10.1515/spp-2017-0006

Vancouver

Author

Amador, Julio ; Collignon, Sofia ; Benoit, Kenneth ; Akitaka, Matsuo. / Predicting the Brexit Vote by Tracking and Classifying Public Opinion Using Twitter Data. In: Statistics, Politics and Policy. 2017 ; Vol. 8, No. 1. pp. 85-104.

BibTeX

@article{d60729dbf0174743a18cd129ef73a094,
title = "Predicting the Brexit Vote by Tracking and Classifying Public Opinion Using Twitter Data",
abstract = "We use 23M Tweets related to the EU referendum in the UK to predict the Brexit vote. In particular, we use user-generated labels known as hashtags to build training sets related to the Leave/Remain campaign. Next, we train SVMs in order to classify Tweets. Finally, we compare our results to Internet and telephone polls. This approach not only allows to reduce the time of hand-coding data to create a training set, but also achieves high level of correlations with Internet polls. Our results suggest that Twitter data may be a suitable substitute for Internet polls and may be a useful complement for telephone polls. We also discuss the reach and limitations of this method.",
author = "Julio Amador and Sofia Collignon and Kenneth Benoit and Matsuo Akitaka",
note = "Amador Diaz Lopez, J. C., Collignon-Delmar, S., Benoit, K., & Matsuo, A. Predicting the Brexit Vote by Tracking and Classifying Public Opinion Using Twitter Data. Statistics, Politics and Policy. 8:1.",
year = "2017",
month = oct,
day = "26",
doi = "10.1515/spp-2017-0006",
language = "English",
volume = "8",
pages = "85--104",
journal = "Statistics, Politics and Policy",
publisher = "DeGruyter, Berlin",
number = "1",

}

RIS

TY - JOUR

T1 - Predicting the Brexit Vote by Tracking and Classifying Public Opinion Using Twitter Data

AU - Amador, Julio

AU - Collignon, Sofia

AU - Benoit, Kenneth

AU - Akitaka, Matsuo

N1 - Amador Diaz Lopez, J. C., Collignon-Delmar, S., Benoit, K., & Matsuo, A. Predicting the Brexit Vote by Tracking and Classifying Public Opinion Using Twitter Data. Statistics, Politics and Policy. 8:1.

PY - 2017/10/26

Y1 - 2017/10/26

N2 - We use 23M Tweets related to the EU referendum in the UK to predict the Brexit vote. In particular, we use user-generated labels known as hashtags to build training sets related to the Leave/Remain campaign. Next, we train SVMs in order to classify Tweets. Finally, we compare our results to Internet and telephone polls. This approach not only allows to reduce the time of hand-coding data to create a training set, but also achieves high level of correlations with Internet polls. Our results suggest that Twitter data may be a suitable substitute for Internet polls and may be a useful complement for telephone polls. We also discuss the reach and limitations of this method.

AB - We use 23M Tweets related to the EU referendum in the UK to predict the Brexit vote. In particular, we use user-generated labels known as hashtags to build training sets related to the Leave/Remain campaign. Next, we train SVMs in order to classify Tweets. Finally, we compare our results to Internet and telephone polls. This approach not only allows to reduce the time of hand-coding data to create a training set, but also achieves high level of correlations with Internet polls. Our results suggest that Twitter data may be a suitable substitute for Internet polls and may be a useful complement for telephone polls. We also discuss the reach and limitations of this method.

U2 - 10.1515/spp-2017-0006

DO - 10.1515/spp-2017-0006

M3 - Article

VL - 8

SP - 85

EP - 104

JO - Statistics, Politics and Policy

JF - Statistics, Politics and Policy

IS - 1

ER -