Effectiveness of Large Language Models in Simulating Regional Psychological Structures: An Empirical Examination of Personality and Subjective Well-being
This research addresses the potential and limitations of using LLMs as virtual participants in large-scale psychological studies, particularly for simulating regional psychological structures, but it is incremental as it builds on existing work with LLMs in social science simulations.
The study investigated whether large language models (LLMs) can simulate culturally grounded psychological patterns by generating virtual participants matched to demographic distributions and comparing them with human responses on personality traits and subjective well-being across seven Chinese regions, finding broad similarity in regional trends but systematic differences such as lower extraversion and openness, higher agreeableness and neuroticism, and consistently lower happiness in simulated data.
This study examines whether LLMs can simulate culturally grounded psychological patterns based on demographic information. Using DeepSeek, we generated 2943 virtual participants matched to demographic distributions from the CFPS2018 and compared them with human responses on the Big Five personality traits and subjective well-being across seven Chinese regions.Personality was measured using a 15-item Chinese Big Five inventory, and happiness with a single-item rating. Results revealed broad similarity between real and simulated datasets, particularly in regional variation trends. However, systematic differences emerged:simulated participants scored lower in extraversion and openness, higher in agreeableness and neuroticism, and consistently reported lower happiness. Predictive structures also diverged: while human data identified conscientiousness, extraversion and openness as positive predictors of happiness, the AI emphasized openness and agreeableness, with extraversion predicting negatively. These discrepancies suggest that while LLMs can approximate population-level psychological distributions, they underrepresent culturally specific and affective dimensions. The findings highlight both the potential and limitations of LLM-based virtual participants for large-scale psychological research and underscore the need for culturally enriched training data and improved affective modeling.