Enhancing Persuasive Dialogue Agents by Synthesizing Cross-Disciplinary Communication Strategies
Shinnosuke Nozue, Yuto Nakano, Yotaro Watanabe, Meguru Takasaki, Shoji Moriya, Reina Akama, Jun Suzuki

TL;DR
This paper introduces a cross-disciplinary framework for persuasive dialogue agents, integrating strategies from social psychology, economics, and communication theory, leading to improved success rates and better persuasion of low-intent individuals.
Contribution
It presents a novel, cross-disciplinary approach to designing persuasive dialogue agents, enhancing their effectiveness and generalizability across diverse scenarios.
Findings
Improved persuasion success rate across datasets
Effective persuasion of individuals with low initial intent
Strong generalizability demonstrated in experiments
Abstract
Current approaches to developing persuasive dialogue agents often rely on a limited set of predefined persuasive strategies that fail to capture the complexity of real-world interactions. We applied a cross-disciplinary approach to develop a framework for designing persuasive dialogue agents that draws on proven strategies from social psychology, behavioral economics, and communication theory. We validated our proposed framework through experiments on two distinct datasets: the Persuasion for Good dataset, which represents a specific in-domain scenario, and the DailyPersuasion dataset, which encompasses a wide range of scenarios. The proposed framework achieved strong results for both datasets and demonstrated notable improvement in the persuasion success rate as well as promising generalizability. Notably, the proposed framework also excelled at persuading individuals with initially…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
Taxonomy
TopicsAI in Service Interactions · Multimodal Machine Learning Applications · Speech and dialogue systems
