Geographically aggregated psychological traits from linguistic analysis of Twitter data predict U.S. voter realignment since 2016

The 2016 U.S. Presidential election heralded the beginning of a political realignment in American politics. A key question for understanding this realignment is whether the Republican party’s shift towards right-wing populism was driven by Donald Trump’s candidacy, versus Trump’s political success being driven by dynamics in the electorate that predated his politicalrise. Individual surveys have commonly been used to address such questions, but there are many limitations to that method, including the cost of data collection and the need for accurate self-reflection on psychological questionnaires. We instead addressed this question by examining a corpus of Twitter posts written between July 2009 and February 2015, aggregated by U.S. county. The geographic distribution of psychological traits (personality, empathy, and moral foundations) was estimated by applying to the aggregated Twitter data lexica quantifying how strongly individual words predict psychological traits. The aggregate personality measures were then used to predict vote share for Donald Trump from 2016 to 2024, controlling for a baseline of prior Republican support. Low agreeableness predicts greater support for Trump, a novel result relative to other geographically aggregated data but consistent with prior survey findings relating this trait to right-wing populism. Low empathic concern and the degree to which tweets reference unfairness and defilement also predict shifts towards Trump. Our analysis suggests that people in geographic regions that shifted rightward beginning in 2016 were already expressing emotions consistent with Donald Trump’s messaging in their social media postings before his political rise.