Understanding Fortunetelling with Large Language Models in China: User Practices, Perceptions, and Impacts on Beliefs and Decisions

2026-07-17

AI Summary

This study investigates how the emerging practice of using large language models (LLMs) for fortune-telling influences Chinese users’ psychological states, beliefs, and decision-making. Through content analysis of 1,045 Chinese social media posts and semi-structured interviews with 20 users, the research establishes the first taxonomy categorizing LLM-generated fortune-telling content, users’ emotional responses, and perceived credibility. Findings indicate that while users rarely alter their core decisions based on fortune-telling outcomes, they frequently experience subtle shifts in mindset and minor behavioral adjustments. These patterns suggest that LLM-based fortune-telling primarily functions as a source of emotional support and companionship rather than as a predictive instrument. The study thereby illuminates the socio-psychological mechanisms underlying AI deployment in irrational contexts and extends our understanding of the affective dimensions of human–AI interaction.

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.

Problem

• fortunetelling
• large language models
• user perceptions
• belief impact
• decision-making

Innovation

• Large Language Models
• Fortunetelling
• Qualitative Study
• User Perception
• Emotional Support