Rhetoric Mining: A New Text-Analytics Approach for Quantifying Persuasion

Abstract

Rhetoric mining is a novel text-analytics method for quantifying persuasion based on rhetorical analysis theory. Our mixed-methodology approach combines qualitative context analysis with automated tagging and quantification of rhetorical moves. Rhetorical moves are complex discursive patterns and, thus, require a sequence-based text-mining approach, rather than the simpler word-based frequency analyses. We apply a sequence-alignment method to detect semantically equivalent sequences with high precision and efficiency. We illustrate our method by analyzing arguments used to justify stock picks in an online investment community. For these data, we detect and quantify the rhetorical moves of ethos (personal versus cited expertise), hedging (confidence versus uncertainty), and evidence type (product-, company-, or stock-based evidence). We use rhetoric mining to identify argument styles of persuasiveness (pitches that receive community recommendations) and trustworthiness (pitches that are written by successful investors). Rhetoric mining provides a new analytic lens in Information Systems research to analyze the influence of persuasion in consumer decision making. History: W. Nick Street served as the senior editor for this article. Data Ethics & Reproducibility Note: The code capsule is available on Code Ocean at https://codeocean.com/capsule/9373643/tree/v1 and in the e-Companion to this article (available at https://doi.org/10.1287/ijds.2022.0024 ).