Analyzing Human Heuristics and Strategies in Everyday Decision-Making Conversations for Conversational AI Design
Provides empirical grounding for designing conversational AI that aligns with human heuristic decision-making processes, addressing a gap in current data-centric systems.
Analyzed 955 Korean conversations (15,476 utterances) about food and travel decisions, finding that people prioritize satisficing over optimization and rely on internal knowledge and interactional strategies. Identified a frequency-efficiency mismatch where prevalent heuristics sustain exploration while infrequent rule-based strategies drive resolution.
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.