Can large language models interpret unstructured chat data on dynamic group decision-making processes? Evidence on joint destination choice

TL;DR

This paper investigates the capability of large language models to interpret unstructured chat data for understanding group decision-making processes, specifically in joint destination choices, highlighting their strengths and limitations.

Contribution

The study introduces a prompting framework that enables LLMs to extract structured decision-making factors from unstructured group chat data, demonstrating automation potential and identifying current limitations.

Findings

LLMs reliably extract explicit decision factors

Struggle to identify nuanced implicit factors

Context-dependent trust in LLM outputs

Abstract

Social activities result from complex joint activity-travel decisions between group members. While observing the decision-making process of these activities is difficult via traditional travel surveys, the advent of new types of data, such as unstructured chat data, can help shed some light on these complex processes. However, interpreting these decision-making processes requires inferring both explicit and implicit factors. This typically involves the labor-intensive task of manually annotating dialogues to capture context-dependent meanings shaped by the social and cultural norms. This study evaluates the potential of Large Language Models (LLMs) to automate and complement human annotation in interpreting decision-making processes from group chats, using data on joint eating-out activities in Japan as a case study. We designed a prompting framework inspired by the knowledge acquisition process, which sequentially extracts key decision-making factors, including the group-level restaurant choice set and outcome, individual preferences of each alternative, and the specific attributes driving those preferences. This structured process guides the LLM to interpret group chat data, converting unstructured dialogues into structured tabular data describing decision-making factors. To evaluate LLM-driven outputs, we conduct a quantitative analysis using a human-annotated ground truth dataset and a qualitative error analysis to examine model limitations. Results show that while the LLM reliably captures explicit decision-making factors, it struggles to identify nuanced implicit factors that human annotators readily identified. We pinpoint specific contexts when LLM-based extraction can be trusted versus when human oversight remains essential. These findings highlight both the potential and limitations of LLM-based analysis for incorporating non-traditional data sources on social activities.