Predicting Elections for Multiple Countries Using Twitter and Polls

被引：41

作者：

Tsakalidis, Adam ^{[1
,2
]}

Papadopoulos, Symeon ^{[1
]}

Cristea, Alexandra I. ^{[3
]}

Kompatsiaris, Yiannis ^{[1
]}

机构：

[1] Ctr Res & Technol Hellas, Inst Informat Technol, Hellas, Greece

[2] Univ Warwick, Urban Sci, Coventry CV4 7AL, W Midlands, England

[3] Univ Warwick, Intelligent & Adapt Syst Res Grp, Coventry CV4 7AL, W Midlands, England

来源：

IEEE INTELLIGENT SYSTEMS | 2015年 / 30卷 / 02期

基金：

英国工程与自然科学研究理事会;

关键词：

elections; intelligent systems; machine learning; time-series forecasting; Twitter; Web mining;

D O I：

10.1109/MIS.2015.17

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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. © 2001-2011 IEEE.

引用

页码：10 / 17

页数：8

共 10 条

[1]

[Anonymous], 2013, P 7 INT AAAI C WEBL

[2]

[Anonymous], 2005, Proceedings of the ACL Student Research Workshop, ACLstudent '05, DOI DOI 10.3115/1628960.1628969

[3]

[Anonymous], 2010, ICWSM

[4]

[Anonymous], 2010, P INT AAAI C WEB SOC

[5] A Meta-Analysis of State-of-the-Art Electoral Prediction From Twitter Data [J].

Gayo-Avello, Daniel .

SOCIAL SCIENCE COMPUTER REVIEW, 2013, 31 (06) :649-679

[6]

Lampos V., 2013, P 51 ANN M ASS COMPU, P993

[7]

Metaxas P.T., 2011, PRIVACY SECURITY RIS, P165, DOI [10.1109/PASSAT/SocialCom.2011.98, DOI 10.1109/PASSAT/SOCIALCOM.2011.98]

[8]

Sang E. T. K., 2012, P WORKSH SEM AN SOC, P53

[9]

Shi L., 2012, Predicting US Primary Elections with Twitter

[10]

Tjong Erik., 2011, P WORKSHOP SEMANTIC, P53

← 1 →