Problem
Research questions and friction points this paper is trying to address.
Conversational AI
human heuristics
everyday decision-making
interactional strategies
satisficing
Analyzing Human Heuristics and Strategies in Everyday Decision-Making Conversations for Conversational AI Design
🤖 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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
heuristics
conversational AI
satisficing
cognitive load
decision-making strategies
🔎 Similar Papers
No similar papers found.
