113th Congress as News Commentators on Twitter

Abstract

Congress members commentate on newsworthy events selectively based on their political agenda, not only on broadcast media but also on social media outlets. In this study, I introduce a method to measure this selectivity (for agenda setting) using curated tweets of Congress members. I showed that political groups of the monitored members of 113th Congress can be predicted with more than 95% accuracy just by looking at the topics they talk (and do not talk) about. In order to do this, I first created a co-commentation network where the vertices are congress people and the edge weights are the number of common newsworthy events (headlines) that they have commentated on between January 2013 and January 2015 (i.e. during 113th Congress). Then, I detected the communities in this network by employing a weighted modularity clustering algorithm. Using this method, two groups are detected when the highest modularity achieved, as a result, 62 of the 65 monitored Congress members are found to be in the same group as their co-party members. In this study, I also showed the newsworthy tweet activity of congresspeople and political groups and introduce methods to measure the politicization and political polarity of events. Our entire dataset consists of 7,376 news published between January 2013 and January 2015 on theplazz.com news site, as well as 156,480 commentary tweets of 1442 newsmakers on these news events. All the tweets are curated manually by theplazz.com editors. This study uses a unique dataset collected by the author, and effectively uses network analysis to measure politicians' agenda similarity. It contributes to the field by shedding light on the online agenda building efforts of politicians.

Keywords: agenda building, agenda setting, congress, social network analysis, computational social science