Searching and Clustering Methodologies: Connecting Political Communication Content across Platforms

被引:11
|
作者
Driscoll, Kevin [1 ]
Thorson, Kjerstin [2 ]
机构
[1] Microsoft Res, Gurgaon, Haryana, India
[2] USCs Annenberg Sch Commun & Journalism, Los Angeles, CA USA
关键词
political communication; social media; content analysis; cluster analysis; text mining; MEDIA; TWITTER;
D O I
10.1177/0002716215570570
中图分类号
D0 [政治学、政治理论];
学科分类号
0302 ; 030201 ;
摘要
People create, consume, and share content online in increasingly complex ways, often including multiple news, entertainment, and social media platforms. This article explores methods for tracing political media content across overlapping communication infrastructures. Using the 2011 Occupy Movement protests and 2013 consumer boycotts as cases, we illustrate methods for creating integrated datasets of political event-related social media content by (1) using fixed URLs to link posts across platforms (URL-based integration) and (2) using semiautomated text clustering to identify similar posts across social networking services (thematic integration). These approaches help to reveal biases in the way that we characterize political communication practices that may occur when we focus on a single platform in isolation.
引用
收藏
页码:134 / 148
页数:15
相关论文
共 50 条