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 journal › Article › peer-review
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 journal › Article › peer-review
}
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 -