For the majority of votes that take place in Congress, over 90% of legislators' votes can be explained purely by ideology. In years when no party has a significant majority, party unity becomes imperative in the scope of advancing the party's agenda. Various theories seek to explain congressional voting behavior as a catch-all approach, and often fail to further our understanding of the inconsistencies in voting behavior. Our lack of understanding of against party-line voting hinders our ability to explain and predict voting behavior. This project seeks to utilize various machine learning techniques to gain a better understanding of what causes against party-line voting in Congress.
van Doorn, Bas
Computer Science; Political Science
O'Neill, John W., "A Machine Learning Approach To Understanding Against Party-Line Voting in Congress" (2017). Senior Independent Study Theses. Paper 7601.
machine learning, congressional voting, party line, voting behavior
Bachelor of Arts
Senior Independent Study Thesis
© Copyright 2017 John W. O'Neill