Social Network Influence on Electoral Outcomes

Abstract

Social networks tend to shape our views about the world. Our study conducts an empirical analysis on social network dynamics using Twitter data; specifically, this research analyzes how social networks aect political decisions. We study how social networks influence voting decisions and determine whether or not people vote ‘correctly’ based on their tweets or what they believe. We collect Twitter data on a daily basis which allows us to gather dynamic social network measurements. We collected tweets before, during, and after the 2012 Presidential election and analyze the content to see if we can predict how people will vote. We are able to identify how these individuals ‘should’ vote based on their ideological, lexicographic profile. We use lexicographical analysis to check if ideological key words are present in a user’s tweets and if the overall sentiment on this issue was positive or negative. We utilize this data to determine how people should have voted. These results may conflict with an individual’s verbal declaration of political ideology. We are able to determine what percentage of the population voted correctly in the last election. Additionally, we examine the social network structure in Twitter and how it aects voting. We show that an individual’s political ideology is influenced by others in their network.