Using sentiment analysis to define twitter political users' classes and their homophily during the 2016 American presidential election

被引：35

作者：

Caetano, Josemar A. ^{[1
]}

Lima, Helder S. ^{[1
]}

Santos, Mateus F. ^{[1
]}

Marques-Neto, Humberto T. ^{[1
]}

机构：

[1] Pontifical Catholic Univ Minas Gerais PUC Minas, Dept Comp Sci, Belo Horizonte, MG, Brazil

来源：

JOURNAL OF INTERNET SERVICES AND APPLICATIONS | 2018年 / 9卷 / 01期

关键词：

Internet; Online social networks; Sentiment analysis; Homophily;

D O I：

10.1186/s13174-018-0089-0

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper proposes an analysis of political homophily among Twitter users during the 2016 American Presidential Election. We collected 4.9 million tweets of 18,450 users and their contact network from August 2016 to November 2016. We defined six user classes regarding their sentiment towards Donald Trump and Hillary Clinton: whatever, Trump supporter, Hillary supporter, positive, neutral, and negative. Next, we analyzed their political homophily in three scenarios. Firstly, we analyzed the Twitter follow, mention and retweet connections either unidirectional and reciprocal. In the second scenario, we analyzed multiplex connections, and in the third one, we analyzed friendships with similar speeches. Our results showed that negative users, users supporting Trump, and users supporting Hillary had homophily in all analyzed scenarios. We also found out that the homophily level increase when there are reciprocal connections, similar speeches, or multiplex connections.

引用

页数：15

共 36 条

[1]

[Anonymous], 2016, TIMES TNW

[2] Tweeting From Left to Right: Is Online Political Communication More Than an Echo Chamber? [J].

Barbera, Pablo ;

Jost, John T. ;

Nagler, Jonathan ;

Tucker, Joshua A. ;

Bonneau, Richard .

PSYCHOLOGICAL SCIENCE, 2015, 26 (10) :1531-1542

[3] Latent Dirichlet allocation [J].

Blei, DM ;

Ng, AY ;

Jordan, MI .

JOURNAL OF MACHINE LEARNING RESEARCH, 2003, 3 (4-5) :993-1022

[4] Emotion shapes the diffusion of moralized content in social networks [J].

Brady, William J. ;

Wills, Julian A. ;

Jost, John T. ;

Tucker, Joshua A. ;

Van Bavel, Jay J. .

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2017, 114 (28) :7313-7318

[5] Status and Friendship: Mechanisms of Social Network Evolution [J].

Brandt, Christina ;

Leskovec, Jure .

WWW'14 COMPANION: PROCEEDINGS OF THE 23RD INTERNATIONAL CONFERENCE ON WORLD WIDE WEB, 2014, :229-230

[6]

Caetano JA, 6 BRAZ WORKSH SOC NE

[7] RELATIONAL ANALYSIS - THE STUDY OF SOCIAL ORGANIZATIONS WITH SURVEY METHODS [J].

COLEMAN, JS .

HUMAN ORGANIZATION, 1958, 17 (04) :28-36

[8] Echo Chamber or Public Sphere? Predicting Political Orientation and Measuring Political Homophily in Twitter Using Big Data [J].

Colleoni, Elanor ;

Rozza, Alessandro ;

Arvidsson, Adam .

JOURNAL OF COMMUNICATION, 2014, 64 (02) :317-332

[9] An Economic Model of Friendship: Homophily, Minorities, and Segregation [J].

Currarini, Sergio ;

Jackson, Matthew O. ;

Pin, Paolo .

ECONOMETRICA, 2009, 77 (04) :1003-1045

[10] A Survey and Comparative Study of Tweet Sentiment Analysis via Semi-Supervised Learning [J].

Da Silva, Nadia Felix F. ;

Coletta, Luiz F. S. ;

Hruschka, Eduardo R. .

ACM COMPUTING SURVEYS, 2016, 49 (01)

← 1 2 3 4 →