Seamlessly Integrating Factual Information and Social Content with Persuasive Dialogue

TL;DR

This paper introduces a modular dialogue system that effectively combines factual and social content to enhance persuasive conversations, outperforming traditional end-to-end models in user evaluations.

Contribution

The work presents a novel, generalizable framework for integrating social and factual information into persuasive dialogue systems, improving user perception.

Findings

Framework received higher user ratings in competence and friendliness.

Explicit handling of social content improves dialogue quality.

Outperforms baseline end-to-end models in evaluations.

Abstract

Complex conversation settings such as persuasion involve communicating changes in attitude or behavior, so users' perspectives need to be addressed, even when not directly related to the topic. In this work, we contribute a novel modular dialogue system framework that seamlessly integrates factual information and social content into persuasive dialogue. Our framework is generalizable to any dialogue tasks that have mixed social and task contents. We conducted a study that compared user evaluations of our framework versus a baseline end-to-end generation model. We found our framework was evaluated more favorably in all dimensions including competence and friendliness, compared to the end-to-end model which does not explicitly handle social content or factual questions.