Analyzing Human Heuristics and Strategies in Everyday Decision-Making Conversations for Conversational AI Design

2026-05-08

AI Summary

This study addresses the gap in current dialogue AI systems, which predominantly rely on data-driven reasoning while overlooking the heuristic and interactive strategies humans employ in natural conversation. Drawing on a corpus of 955 authentic Korean dialogues (15,476 utterances) about food and travel decisions, the authors developed a decision annotation scheme grounded in cognitive theory and leveraged large language models to support systematic coding. Their analysis reveals that human interlocutors favor satisficing over optimizing solutions, with high-frequency heuristic strategies sustaining conversational fluency during exploration phases, whereas low-frequency rule-based strategies prove more efficient in exploitation phases—highlighting a mismatch between strategy frequency and efficacy. These findings offer empirical grounding for designing dialogue AI that aligns with human heuristic decision-making, thereby enhancing its naturalness and effectiveness in everyday interactions.

Abstract

Conversational AI increasingly supports everyday decision-making, yet most systems rely on data-centric reasoning rather than the heuristic and interactional strategies people use in natural conversation. To ground design in actual human practice, we analyze 955 real-world Korean conversations (15,476 utterances) involving food and travel decisions, applying a decision-making codebook through an LLM-assisted coding pipeline. Our findings reveal that people prioritize satisficing over optimization, relying heavily on internal knowledge and interactional strategies to manage cognitive load. Critically, we identify a frequency-efficiency mismatch: the most prevalent heuristics sustain conversational flow during exploration, whereas infrequent, rule-based strategies are highly effective at driving resolution during exploitation. By mapping how these patterns transfer across the spectrum of human-AI interaction, this work provides empirical grounding consistent with cognitive theories of decision-making and offers design implications that align AI systems with human heuristic processes.

Problem

• Conversational AI
• human heuristics
• everyday decision-making
• interactional strategies
• satisficing

Innovation

• heuristics
• conversational AI
• satisficing
• cognitive load
• decision-making strategies