AutoPersuade: A Framework for Evaluating and Explaining Persuasive Arguments

TL;DR

AutoPersuade is a comprehensive framework that constructs, evaluates, and explains persuasive arguments using a new dataset, a topic model for feature identification, and effectiveness prediction validated through human studies.

Contribution

It introduces a novel three-part framework combining dataset curation, topic modeling, and causal analysis for persuasive argument evaluation and explanation.

Findings

Effective prediction of argument persuasiveness

Validated with human studies on veganism arguments

Outperforms baseline models in effectiveness prediction

Abstract

We introduce AutoPersuade, a three-part framework for constructing persuasive messages. First, we curate a large dataset of arguments with human evaluations. Next, we develop a novel topic model to identify argument features that influence persuasiveness. Finally, we use this model to predict the effectiveness of new arguments and assess the causal impact of different components to provide explanations. We validate AutoPersuade through an experimental study on arguments for veganism, demonstrating its effectiveness with human studies and out-of-sample predictions.