Predicting Political Orientation of News Articles Based on User Behavior Analysis in Social Network

Jun-Gil KIM; Kyung-Soon LEE

doi:10.1587/transinf.E97.D.685

Open Access
Predicting Political Orientation of News Articles Based on User Behavior Analysis in Social Network

Jun-Gil KIM, Kyung-Soon LEE

Full Text Views

97

Share
Cite this

Free PDF (833.1KB)

Summary :

News articles usually represent a biased viewpoint on contentious issues, potentially causing social problems. To mitigate this media bias, we propose a novel framework for predicting orientation of a news article by analyzing social user behaviors in Twitter. Highly active users tend to have consistent behavior patterns in social network by retweeting behavior among users with the same viewpoints for contentious issues. The bias ratio of highly active users is measured to predict orientation of users. Then political orientation of a news article is predicted based on the bias ratio of users, mutual retweeting and opinion analysis of tweet documents. The analysis of user behavior shows that users with the value of 1 in bias ratio are 88.82%. It indicates that most of users have distinctive orientation. Our prediction method based on orientation of users achieved 88.6% performance in accuracy. Experimental results show significant improvements over the SVM classification. These results show that proposed detection method is effective in social network.

Publication: IEICE TRANSACTIONS on Information Vol.E97-D No.4 pp.685-693

Publication Date: 2014/04/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E97.D.685

Type of Manuscript: Special Section PAPER (Special Section on Data Engineering and Information Management)

Category

Authors

Jun-Gil KIM
CAIIT, Chonbuk National University
Kyung-Soon LEE
CAIIT, Chonbuk National University

Keyword

social network, user behavior analysis, political orientation, bias ratio, mutual retweet

Cite this

Copy

Jun-Gil KIM, Kyung-Soon LEE, "Predicting Political Orientation of News Articles Based on User Behavior Analysis in Social Network" in IEICE TRANSACTIONS on Information, vol. E97-D, no. 4, pp. 685-693, April 2014, doi: 10.1587/transinf.E97.D.685.
Abstract: News articles usually represent a biased viewpoint on contentious issues, potentially causing social problems. To mitigate this media bias, we propose a novel framework for predicting orientation of a news article by analyzing social user behaviors in Twitter. Highly active users tend to have consistent behavior patterns in social network by retweeting behavior among users with the same viewpoints for contentious issues. The bias ratio of highly active users is measured to predict orientation of users. Then political orientation of a news article is predicted based on the bias ratio of users, mutual retweeting and opinion analysis of tweet documents. The analysis of user behavior shows that users with the value of 1 in bias ratio are 88.82%. It indicates that most of users have distinctive orientation. Our prediction method based on orientation of users achieved 88.6% performance in accuracy. Experimental results show significant improvements over the SVM classification. These results show that proposed detection method is effective in social network.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.E97.D.685/_p

Copy

@ARTICLE{e97-d_4_685,
author={Jun-Gil KIM, Kyung-Soon LEE, },
journal={IEICE TRANSACTIONS on Information},
title={Predicting Political Orientation of News Articles Based on User Behavior Analysis in Social Network},
year={2014},
volume={E97-D},
number={4},
pages={685-693},
abstract={News articles usually represent a biased viewpoint on contentious issues, potentially causing social problems. To mitigate this media bias, we propose a novel framework for predicting orientation of a news article by analyzing social user behaviors in Twitter. Highly active users tend to have consistent behavior patterns in social network by retweeting behavior among users with the same viewpoints for contentious issues. The bias ratio of highly active users is measured to predict orientation of users. Then political orientation of a news article is predicted based on the bias ratio of users, mutual retweeting and opinion analysis of tweet documents. The analysis of user behavior shows that users with the value of 1 in bias ratio are 88.82%. It indicates that most of users have distinctive orientation. Our prediction method based on orientation of users achieved 88.6% performance in accuracy. Experimental results show significant improvements over the SVM classification. These results show that proposed detection method is effective in social network.},
keywords={},
doi={10.1587/transinf.E97.D.685},
ISSN={1745-1361},
month={April},}

Copy

TY - JOUR
TI - Predicting Political Orientation of News Articles Based on User Behavior Analysis in Social Network
T2 - IEICE TRANSACTIONS on Information
SP - 685
EP - 693
AU - Jun-Gil KIM
AU - Kyung-Soon LEE
PY - 2014
DO - 10.1587/transinf.E97.D.685
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E97-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2014
AB - News articles usually represent a biased viewpoint on contentious issues, potentially causing social problems. To mitigate this media bias, we propose a novel framework for predicting orientation of a news article by analyzing social user behaviors in Twitter. Highly active users tend to have consistent behavior patterns in social network by retweeting behavior among users with the same viewpoints for contentious issues. The bias ratio of highly active users is measured to predict orientation of users. Then political orientation of a news article is predicted based on the bias ratio of users, mutual retweeting and opinion analysis of tweet documents. The analysis of user behavior shows that users with the value of 1 in bias ratio are 88.82%. It indicates that most of users have distinctive orientation. Our prediction method based on orientation of users achieved 88.6% performance in accuracy. Experimental results show significant improvements over the SVM classification. These results show that proposed detection method is effective in social network.
ER -