Understanding Persuasive Interactions between Generative Social Agents and Humans: The Knowledge-based Persuasion Model (KPM)

TL;DR

The paper addresses the lack of theory for persuasive interactions between Generative Social Agents (GSAs) and humans and introduces the Knowledge-based Persuasion Model (KPM) to fill this gap. The KPM combines agent knowledge (self-, user-, and context-knowledge), agent persuasive behavior (message content and delivery), and user response within a context layer to explain how knowledge informs GSA persuasion and human processing. It outlines four prerequisites for empirical testing and provides preliminary indicators across the dimensions, aiming to guide responsible design and evaluation. The framework has practical implications for healthcare and education, offering a pathway to enhance wellbeing while mitigating manipulation, through knowledge-based design requirements and robust ethical safeguards.

Abstract

Generative social agents (GSAs) use artificial intelligence to autonomously communicate with human users in a natural and adaptive manner. Currently, there is a lack of theorizing regarding interactions with GSAs, and likewise, few guidelines exist for studying how they influence user attitudes and behaviors. Consequently, we propose the Knowledge-based Persuasion Model (KPM) as a novel theoretical framework. According to the KPM, a GSA's self, user, and context-related knowledge drives its persuasive behavior, which in turn shapes the attitudes and behaviors of a responding human user. By synthesizing existing research, the model offers a structured approach to studying interactions with GSAs, supporting the development of agents that motivate rather than manipulate humans. Accordingly, the KPM encourages the integration of responsible GSAs that adhere to social norms and ethical standards with the goal of increasing user wellbeing. Implications of the KPM for research and application domains such as healthcare and education are discussed.

Figures (3)

• Figure 1: Comparison between research approaches for rule-based agents and GSAs
• Figure 2: The Persuasion Knowledge Model by Friestad and Wright friestadPersuasionKnowledgeModel1994
• Figure 3: The Knowledge-based Persuasion Model (KPM) for persuasive interactions between GSAs and humans