Enhancing Persuasive Dialogue Agents by Synthesizing Cross-Disciplinary Communication Strategies
This work is significant for researchers and developers of persuasive dialogue agents, as it offers a more comprehensive and effective approach to designing agents that can persuade individuals, especially those initially resistant.
The paper addresses the limitation of current persuasive dialogue agents that use a limited set of strategies by developing a cross-disciplinary framework. This framework, drawing from social psychology, behavioral economics, and communication theory, achieved strong results and improved persuasion success rates on two distinct datasets, notably excelling at persuading individuals with initially low intent.
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 low intent, which addresses a critical challenge for persuasive dialogue agents.