Skip to content

text mining analysis of asymmetry in US parties' sentiments

Notifications You must be signed in to change notification settings

timdeisemann/MiningForMeaning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 

Repository files navigation

MiningForMeaning

text mining analysis of asymmetry in US parties' sentiments

The advent of the election campaign for the US presidential elections in 2020 motivates a comparative analysis of the two major parties involved. In this framework the claim of "Ideological Republicans and Group Interest Democrats: The Asymmetry of American Party Politics" by Grossmann and Hopkins (2015) can be quantitatively tested with the application of sentiment analysis using mined Twitter data.

This analysis serves in particular as an example to show the possibilities as well as the limits of text mining in social science research. This goal is achieved as it emerges that there may often be large differences between the results of a manually manageable text analysis (small n of party elites) and an algorithmic method of text processing (large n of US senate members). Clearly, some assumed patterns must be discarded and others can only be identified when studying large data sets such as convergence of the emotion level in several categories or the possibility of an opposition effect.

About

text mining analysis of asymmetry in US parties' sentiments

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages