Data mining syllabic patterns in US political party platforms

Political party platforms lay the groundwork for campaigns and messaging in US presidential elections. We conducted an extensive data mining analysis of the syllabic content in every Democratic and Republican party platform from 1856 to 2012. Our techniques revealed marked differences in the syllabic patterns of platforms from the two major parties over different historical eras. Since the rise of radio broadcasting, significant distinguishing syllabic distributions have been identified between Democratic and Republican platforms through our statistical analysis. Voting data was then analyzed to determine if correlations exist between platform syllabic patterns uncovered through our data mining work and presidential election outcomes. Overall, this research applied natural language processing and statistical methods to surface important insights from the vast text data contained in decades of US political party platforms.