Replication Data for: Understanding the Success and Failure of Online Political Debate: Experimental Evidence using Large Language Models

Online political discourse is frequently lamented for being toxic, partisan, and counter-productive. Yet, we know surprisingly little about how core elements of political discourse (justification, tone, willingness to compromise, and partisanship) affect the quality of online political debate. Using text-based treatments experimentally manipulated with a Large Language Model, we test how these elements causally affect the quality of open-text responses about issues important to members of the US and UK publics. We find substantial evidence that differences in justification, tone, and willingness to compromise, but not partisanship, affect the quality of subsequent discourse. Combined, these elements increase the probability of high-quality responses by roughly 1.6 to 2 times and substantially increase openness to alternative viewpoints. Yet despite the ability to bring about substantial changes in discourse quality, we find no evidence that doing so affects political attitudes themselves. Our findings demonstrate how adapting approaches to online debate can foster healthy democratic interactions, but have less influence on changing minds.