The Influence of Prior Discourse on Conversational Agent-Driven Decision-Making

2025-03-06

AI Summary

This study investigates how prior dialogue task complexity moderates the impact of conversational agents’ “nudging” strategies on user decision-making, focusing on cognitive mechanisms underlying default heuristics such as status-quo bias. Method: A between-subjects randomized controlled experiment was conducted, integrating Samuelson’s classic three-scenario paradigm with effect-size analysis to systematically examine the moderating role of task complexity in conversational nudging. Contribution/Results: Results demonstrate that high-complexity dialogue histories significantly enhance nudging efficacy—achieving statistical significance even in single-scenario analyses—revealing a positive association between dialogue history depth and behavioral bias strength. This provides novel empirical evidence on the dynamics of cognitive biases in human–AI dialogue and establishes actionable, cognitively grounded design principles for adaptive conversational interventions calibrated to users’ cognitive load.

Technology Category

• Humans and AI: Learning Human Values and Preferences
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments

Abstract

Persuasion through conversation has been the focus of much research. Nudging is a popular strategy to influence decision-making in physical and digital settings. However, conversational agents employing"nudging"have not received significant attention. We explore the manifestation of cognitive biases-the underlying psychological mechanisms of nudging-and investigate how the complexity of prior dialogue tasks impacts decision-making facilitated by conversational agents. Our research used a between-group experimental design, involving 756 participants randomly assigned to either a simple or complex task before encountering a decision-making scenario. Three scenarios were adapted from Samuelson's classic experiments on status-quo bias, the underlying mechanism of default nudges. Our results aligned with previous studies in two out of three simple-task scenarios. Increasing task complexity consistently shifted effect-sizes toward our hypothesis, though bias was significant in only one case. These findings inform conversational nudging strategies and highlight inherent biases relevant to behavioural economics.

Problem

• Explores cognitive biases in conversational agent-driven decision-making.
• Investigates impact of prior dialogue complexity on decision outcomes.
• Analyzes nudging strategies in conversational agents for behavioral economics.

Innovation

• Explored cognitive biases in conversational nudging
• Used between-group experimental design with 756 participants
• Adapted scenarios from Samuelson's status-quo bias experiments