Quantifying Political Discussion from the Universe of Facebook Status Updates
24 Pages Posted: 9 Aug 2013
Date Written: August 8, 2013
Abstract
The Internet has fundamentally changed the way we conceptualize public opinion, even beyond the way it has altered the traditional measurement of public attitudes and behaviors using random sampling of the broader population. The data analyzed in this paper offer one of the first comprehensive evaluations of mass political discourse generated via messages posted publicly on Facebook (called “status updates”), and allow us to quantify political discussion on Facebook without relying on self-reported behavior, or data from a limited topical context or sample. We find that while less than 1% of the users who post status updates on Facebook on a given day post a political status update, discussion is remarkably responsive to real-world political events. We suggest that instead of thinking of social media data simply as a measurement tool, we re-conceptualize it as both a way to monitor public discourse and also as a driver of public opinion.
Keywords: Facebook, political discussion, health care reform, 2008 election
Suggested Citation: Suggested Citation
Do you have a job opening that you would like to promote on SSRN?
Recommended Papers
-
Making the Most Of Statistical Analyses: Improving Interpretation and Presentation
By Gary King, Michael Tomz, ...
-
Logistic Regression in Rare Events Data
By Gary King and Langche Zeng
-
A Statistical Model for Multiparty Electoral Data
By Jonathan N. Katz and Gary King
-
Explaining Rare Events in International Relations
By Gary King and Langche Zeng
-
Improving Quantitative Studies of International Conflict: A Conjecture
By Nathaniel Beck, Gary King, ...
-
Improving Forecasts of State Failure
By Gary King and Langche Zeng
-
Estimating Risk and Rate Levels, Ratios, and Differences in Case-Control Studies
By Gary King and Langche Zeng
-
By Gary King and Christopher Murray
-
Proper Nouns and Methodological Propriety: Pooling Dyads in International Relations Data
By Gary King