Examining the Ordering of Rhetorical Strategies in Persuasive Requests

• DOI: 10.18653/v1/2020.findings-emnlp.116
• Publication Date: 2020-11-29T09:58:51Z
• Authors: Omar Shaikh; Jiaao Chen; Jon Saad-Falcon; Polo Chau; Diyi Yang
• Keywords: Autoencoder; Content (measure theory)

Interpreting how persuasive language influences audiences has implications across many domains like advertising, argumentation, and propaganda. Persuasion relies on more than a message's content. Arranging the order of message itself (i.e., ordering specific rhetorical strategies) also plays an important role. To examine strategy orderings contribute to persuasiveness, we first utilize Variational Autoencoder model disentangle content strategies in textual requests from large-scale loan request corpus. We then visualize interplay between through attentional LSTM that predicts success requests. find (orderings of) interact uniquely with request's impact rate, thus persuasiveness request.