AutoPersuade: A Framework for Evaluating and Explaining Persuasive Arguments
This work addresses the challenge of evaluating and explaining persuasive arguments, which is incremental as it builds on existing methods for argument analysis.
The authors tackled the problem of constructing persuasive messages by introducing AutoPersuade, a framework that uses a novel topic model to predict argument effectiveness and provide explanations, validated through human studies on veganism arguments with out-of-sample predictions.
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.