Understanding Fortunetelling with Large Language Models in China: User Practices, Perceptions, and Impacts on Beliefs and Decisions
Human-Computer Interaction
Summary
The authors studied how people in China use large language models (LLMs) for fortunetelling, which is a way to explore uncertainty in life. They looked at over 1,000 social media posts and talked to 20 users to understand what topics people asked about, their feelings, and how much they trusted the results. They found that users mainly see LLM fortunetelling as a source of emotional comfort rather than accurate predictions, and it rarely changes their main beliefs or decisions but can lead to small shifts in mindset or behavior. The authors suggest this could help people benefit emotionally from using LLMs this way.
Authors
Xueer Lin, Chenyu Li, Shuai Ma, Yuhan Lyu, Zhenhui Peng
Abstract
Fortunetelling is a cultural practice for navigating uncertainty, often associated with people's beliefs and decisions. Fortunetelling with recent large language models (LLMs) introduces new opportunities and risks. This paper conducts qualitative studies to understand users' practices, perceptions, and impacts of LLM fortunetelling in China. We first analyze 1,045 posts on Chinese social media, yielding a comprehensive taxonomy of the diverse foretold topics (e.g., career, romance), emotion reactions (e.g., surprise, worry), and perceived credibility (e.g., doubt, trust) of LLM fortunetelling. Then, we conduct interviews with 20 users of LLM fortunetelling. The findings indicate that users treat LLM fortunetelling as a tool less for accurate prediction but more for emotional support. While the fortunetelling results rarely change users' initial beliefs or decisions, they are associated with subtle mindset shifts, with some users reporting small behavioral adjustments. We discuss implications for gaining benefits from LLM fortunetelling.