Researchers have explored the use of large language models (LLMs) to generate synthetic consumer data for projective techniques, which are methods used to understand consumer associations, emotions, and needs. The study compared LLM-generated responses to human responses in tasks related to city tourism perceptions, analyzing linguistic measures, diversity, and topic models. While LLMs showed significant overlap with human responses in broad topics, differences were observed in style, linguistic structure, and diversity generation. The research provides recommendations for effectively using LLMs for synthetic data generation, including model and prompt selection, while also highlighting their limitations. AI
IMPACT LLMs can potentially streamline market research by generating synthetic consumer data, though careful consideration of model choice and limitations is necessary.
RANK_REASON The cluster contains an academic paper detailing research findings on the application of LLMs. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
