Social Media and Electoral Predictions: A Meta-Analytic Review

Marko SKORIC; Jing LIU; Kokil JAIDKA

Social Media and Electoral Predictions: A Meta-Analytic Review

Marko SKORIC^*, Jing LIU, Kokil JAIDKA

^*Corresponding author for this work

Department of Media and Communication

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

Abstract

Can social media data be used to make reasonably accurate estimates of electoral outcomes? We conducted a meta-analytic review to examine the predictive performance of different features of social media posts and different methods in predicting political elections: (1) content features; and (2) structural features. Across 45 published studies, we find significant variance in the quality of predictions, which on average still lag behind those in traditional survey research. More specifically, our findings that machine learning-based approaches generally outperform lexicon-based analyses, while combining structural and content features yields most accurate predictions.

Original language	English
Title of host publication	32ND Bled eConference Humanizing Technology for a Sustainable Society
Subtitle of host publication	Conference Proceedings
Editors	Andreja Pucihar, Mirjana Kljajić Borštnar, Roger Bons
Publisher	University of Maribor Press
Pages	764-781
ISBN (Electronic)	978-961-286-280-0
Publication status	Published - Jun 2019
Event	32nd Bled eConference Humanizing Technology for a Sustainable Society - Bled, Slovenia Duration: 16 Jun 2019 → 19 Jun 2019 http://bledconference.org

Publication series

Name	Bled eConference Humanizing Technology for a Sustainable Society, BLED - Conference Proceedings

Conference

Conference	32nd Bled eConference Humanizing Technology for a Sustainable Society
Country/Territory	Slovenia
City	Bled
Period	16/06/19 → 19/06/19
Internet address	http://bledconference.org

Research Keywords

social media
Election prediction
Network Feature
Content Feature
Meta-Analytic Review

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

SKORIC, M., LIU, J., & JAIDKA, K. (2019). Social Media and Electoral Predictions: A Meta-Analytic Review. In A. Pucihar, M. K. Borštnar, & R. Bons (Eds.), 32ND Bled eConference Humanizing Technology for a Sustainable Society: Conference Proceedings (pp. 764-781). (Bled eConference Humanizing Technology for a Sustainable Society, BLED - Conference Proceedings). University of Maribor Press.

SKORIC, Marko ; LIU, Jing ; JAIDKA, Kokil. / Social Media and Electoral Predictions : A Meta-Analytic Review. 32ND Bled eConference Humanizing Technology for a Sustainable Society: Conference Proceedings. editor / Andreja Pucihar ; Mirjana Kljajić Borštnar ; Roger Bons. University of Maribor Press, 2019. pp. 764-781 (Bled eConference Humanizing Technology for a Sustainable Society, BLED - Conference Proceedings).

@inproceedings{3d9db69250964ed7bd0f4ceb79e4817a,

title = "Social Media and Electoral Predictions: A Meta-Analytic Review",

abstract = "Can social media data be used to make reasonably accurate estimates of electoral outcomes? We conducted a meta-analytic review to examine the predictive performance of different features of social media posts and different methods in predicting political elections: (1) content features; and (2) structural features. Across 45 published studies, we find significant variance in the quality of predictions, which on average still lag behind those in traditional survey research. More specifically, our findings that machine learning-based approaches generally outperform lexicon-based analyses, while combining structural and content features yields most accurate predictions.",

keywords = "social media, Election prediction, Network Feature, Content Feature, Meta-Analytic Review",

author = "Marko SKORIC and Jing LIU and Kokil JAIDKA",

year = "2019",

month = jun,

language = "English",

series = "Bled eConference Humanizing Technology for a Sustainable Society, BLED - Conference Proceedings",

publisher = "University of Maribor Press",

pages = "764--781",

editor = "Andreja Pucihar and Bor{\v s}tnar, {Mirjana Kljaji{\'c}} and Roger Bons",

booktitle = "32ND Bled eConference Humanizing Technology for a Sustainable Society",

note = "32nd Bled eConference Humanizing Technology for a Sustainable Society ; Conference date: 16-06-2019 Through 19-06-2019",

url = "http://bledconference.org",

}

SKORIC, M, LIU, J & JAIDKA, K 2019, Social Media and Electoral Predictions: A Meta-Analytic Review. in A Pucihar, MK Borštnar & R Bons (eds), 32ND Bled eConference Humanizing Technology for a Sustainable Society: Conference Proceedings. Bled eConference Humanizing Technology for a Sustainable Society, BLED - Conference Proceedings, University of Maribor Press, pp. 764-781, 32nd Bled eConference Humanizing Technology for a Sustainable Society, Bled, Slovenia, 16/06/19.

Social Media and Electoral Predictions: A Meta-Analytic Review. / SKORIC, Marko; LIU, Jing; JAIDKA, Kokil.
32ND Bled eConference Humanizing Technology for a Sustainable Society: Conference Proceedings. ed. / Andreja Pucihar; Mirjana Kljajić Borštnar; Roger Bons. University of Maribor Press, 2019. p. 764-781 (Bled eConference Humanizing Technology for a Sustainable Society, BLED - Conference Proceedings).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Social Media and Electoral Predictions

T2 - 32nd Bled eConference Humanizing Technology for a Sustainable Society

AU - SKORIC, Marko

AU - LIU, Jing

AU - JAIDKA, Kokil

PY - 2019/6

Y1 - 2019/6

N2 - Can social media data be used to make reasonably accurate estimates of electoral outcomes? We conducted a meta-analytic review to examine the predictive performance of different features of social media posts and different methods in predicting political elections: (1) content features; and (2) structural features. Across 45 published studies, we find significant variance in the quality of predictions, which on average still lag behind those in traditional survey research. More specifically, our findings that machine learning-based approaches generally outperform lexicon-based analyses, while combining structural and content features yields most accurate predictions.

AB - Can social media data be used to make reasonably accurate estimates of electoral outcomes? We conducted a meta-analytic review to examine the predictive performance of different features of social media posts and different methods in predicting political elections: (1) content features; and (2) structural features. Across 45 published studies, we find significant variance in the quality of predictions, which on average still lag behind those in traditional survey research. More specifically, our findings that machine learning-based approaches generally outperform lexicon-based analyses, while combining structural and content features yields most accurate predictions.

KW - social media

KW - Election prediction

KW - Network Feature

KW - Content Feature

KW - Meta-Analytic Review

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85091582192&origin=recordpage

UR - http://www.scopus.com/inward/record.url?scp=85091582192&partnerID=8YFLogxK

M3 - RGC 32 - Refereed conference paper (with host publication)

T3 - Bled eConference Humanizing Technology for a Sustainable Society, BLED - Conference Proceedings

SP - 764

EP - 781

BT - 32ND Bled eConference Humanizing Technology for a Sustainable Society

A2 - Pucihar, Andreja

A2 - Borštnar, Mirjana Kljajić

A2 - Bons, Roger

PB - University of Maribor Press

Y2 - 16 June 2019 through 19 June 2019

ER -

SKORIC M, LIU J, JAIDKA K. Social Media and Electoral Predictions: A Meta-Analytic Review. In Pucihar A, Borštnar MK, Bons R, editors, 32ND Bled eConference Humanizing Technology for a Sustainable Society: Conference Proceedings. University of Maribor Press. 2019. p. 764-781. (Bled eConference Humanizing Technology for a Sustainable Society, BLED - Conference Proceedings).

Social Media and Electoral Predictions: A Meta-Analytic Review

Abstract

Publication series

Conference

Research Keywords

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this