Political attitude estimation through Facebook like: a South Korean case study

Muhammad Eka Wijaya; Meer Sadeq Billah; Heejune Ahn

doi:10.1080/02185377.2017.1402357

Political attitude estimation through Facebook like: a South Korean case study

Muhammad Eka Wijaya, Meer Sadeq Billah, Heejune Ahn

Dept. of Electrical and Information Engineering

Seoul National University of Science and Technology (SNUST)

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

Recently numerous studies are conducted to estimate the human personality from the online social activities. This paper develops a comprehensive model for political attitude estimation leveraging the Facebook Like information of the users. We designed a Facebook Crawler that efficiently collects data overcoming the difficulties in crawling Ajax enabled Facebook pages. We show that the category level selection can reduce the data analysis complexity utilizing the sparsity of the huge like-attitude matrix. In the Korean Facebook users’ context, only 28 criteria (3% of the total) can estimate the political polarity of the user with high accuracy (AUC of 0.82).

Original language	English
Pages (from-to)	87-102
Number of pages	16
Journal	Asian Journal of Political Science
Volume	26
Issue number	1
DOIs	https://doi.org/10.1080/02185377.2017.1402357
State	Published - 2 Jan 2018

Keywords

Asian Politics
Facebook Likes
Matrix Reduction
Political Attitude Estimation
SNS
Social Network Data Mining

Access to Document

10.1080/02185377.2017.1402357

Cite this

@article{65ac3924f51d4404979c96db3c6c205b,

title = "Political attitude estimation through Facebook like: a South Korean case study",

abstract = "Recently numerous studies are conducted to estimate the human personality from the online social activities. This paper develops a comprehensive model for political attitude estimation leveraging the Facebook Like information of the users. We designed a Facebook Crawler that efficiently collects data overcoming the difficulties in crawling Ajax enabled Facebook pages. We show that the category level selection can reduce the data analysis complexity utilizing the sparsity of the huge like-attitude matrix. In the Korean Facebook users{\textquoteright} context, only 28 criteria (3\% of the total) can estimate the political polarity of the user with high accuracy (AUC of 0.82).",

keywords = "Asian Politics, Facebook Likes, Matrix Reduction, Political Attitude Estimation, SNS, Social Network Data Mining",

author = "Wijaya, \{Muhammad Eka\} and Billah, \{Meer Sadeq\} and Heejune Ahn",

note = "Publisher Copyright: {\textcopyright} 2017 Informa UK Limited, trading as Taylor \& Francis Group.",

year = "2018",

month = jan,

day = "2",

doi = "10.1080/02185377.2017.1402357",

language = "English",

volume = "26",

pages = "87--102",

journal = "Asian Journal of Political Science",

issn = "0218-5377",

number = "1",

}

TY - JOUR

T1 - Political attitude estimation through Facebook like

T2 - a South Korean case study

AU - Wijaya, Muhammad Eka

AU - Billah, Meer Sadeq

AU - Ahn, Heejune

PY - 2018/1/2

Y1 - 2018/1/2

N2 - Recently numerous studies are conducted to estimate the human personality from the online social activities. This paper develops a comprehensive model for political attitude estimation leveraging the Facebook Like information of the users. We designed a Facebook Crawler that efficiently collects data overcoming the difficulties in crawling Ajax enabled Facebook pages. We show that the category level selection can reduce the data analysis complexity utilizing the sparsity of the huge like-attitude matrix. In the Korean Facebook users’ context, only 28 criteria (3% of the total) can estimate the political polarity of the user with high accuracy (AUC of 0.82).

AB - Recently numerous studies are conducted to estimate the human personality from the online social activities. This paper develops a comprehensive model for political attitude estimation leveraging the Facebook Like information of the users. We designed a Facebook Crawler that efficiently collects data overcoming the difficulties in crawling Ajax enabled Facebook pages. We show that the category level selection can reduce the data analysis complexity utilizing the sparsity of the huge like-attitude matrix. In the Korean Facebook users’ context, only 28 criteria (3% of the total) can estimate the political polarity of the user with high accuracy (AUC of 0.82).

KW - Asian Politics

KW - Facebook Likes

KW - Matrix Reduction

KW - Political Attitude Estimation

KW - SNS

KW - Social Network Data Mining

UR - http://www.scopus.com/inward/record.url?scp=85033726157&partnerID=8YFLogxK

U2 - 10.1080/02185377.2017.1402357

DO - 10.1080/02185377.2017.1402357

M3 - Article

AN - SCOPUS:85033726157

SN - 0218-5377

VL - 26

SP - 87

EP - 102

JO - Asian Journal of Political Science

JF - Asian Journal of Political Science

IS - 1

ER -

Political attitude estimation through Facebook like: a South Korean case study

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this