A Hybrid Theory and Data-driven Approach to Persuasion Detection with Large Language Models

TL;DR

This paper presents a hybrid model combining large language models and psychological features to predict belief change in online discourse, offering new insights into persuasive message characteristics.

Contribution

It introduces a novel hybrid approach using LLM-generated features and psychological theory to improve persuasion detection in social media contexts.

Findings

Epistemic emotion and willingness to share are top predictors of belief change.

The model achieves improved accuracy in predicting successful persuasion.

Insights can aid online influence detection and misinformation mitigation.

Abstract

Traditional psychological models of belief revision focus on face-to-face interactions, but with the rise of social media, more effective models are needed to capture belief revision at scale, in this rich text-based online discourse. Here, we use a hybrid approach, utilizing large language models (LLMs) to develop a model that predicts successful persuasion using features derived from psychological experiments. Our approach leverages LLM generated ratings of features previously examined in the literature to build a random forest classification model that predicts whether a message will result in belief change. Of the eight features tested, \textit{epistemic emotion} and \textit{willingness to share} were the top-ranking predictors of belief change in the model. Our findings provide insights into the characteristics of persuasive messages and demonstrate how LLMs can enhance models of successful persuasion based on psychological theory. Given these insights, this work has broader applications in fields such as online influence detection and misinformation mitigation, as well as measuring the effectiveness of online narratives.