Computational analysis of 100 K choice dilemmas: Decision attributes, trade- off structures, and model- based prediction

• 成果类型: Article
• 署名作者: Bhatia, Sudeep; van Baal, Simon T.; Wang, Feiyi; Walasek, Lukasz
• 署名单位: University of Pennsylvania; University of Leeds; University of Warwick
• 刊物名称: PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
• ISSN/ISSBN: 0027-11261
• DOI: 10.1073/pnas.2406489122
• 发表日期: 2025-04-29
• 关键词: dimensions; motivation; cognition

摘要

We present a dataset of over 100 K textual descriptions of real- life choice dilemmas, obtained from social media posts and large- scale survey data. Using large language models (LLMs), we extract hundreds of choice attributes at play in these dilemmas and map them onto a common representational space. This representation allows us to quantify the broader themes and specific trade- offs inherent in life choices and analyze how they vary across different contexts. We also present our dilemmas to human participants and find that our LLM pipeline, when combined with established decision models, accurately predicts people's choices, outperforming models based on unstructured textual content, demographics, and personality. In this way, our research provides insights into the attributes, outcomes, and goals that underpin life choices, and shows how large- scale LLM- based structure extraction can be used in combination with existing scientific theory to study complex real- world human behavior.