MKTG 556 | Session 9 | AI–Human Hybrids for Marketing Research: Leveraging Large Language Models (LLMs) as Collaborators

MKTG 556 | Session 9 | AI–Human Hybrids for Marketing Research: Leveraging Large Language Models (LLMs) as Collaborators - 2025 Neeraj Arora, Ishita Chakraborty, and Yohei Nishimura Introduction: The authors' main idea is that a hybrid approach combining humans and large language models (LLMs) improves efficiency and effectiveness in marketing research. In qualitative research, they show that LLMs can help with both data generation and analysis; LLMs effectively create sample characteristics, generate synthetic respondents, and conduct and moderate in-depth interviews. The AI–human hybrid produces information-rich, coherent data that exceeds human-only data in depth and insightfulness and matches human performance in tasks like generating themes and summaries. Evidence from expert judges indicates that humans and LLMs have complementary skills; the human–LLM hybrid outperforms either humans or LLMs alone. For quantitative research, the LLM correctly identifies the answer's direction and valence, with the quality of synthetic data greatly improving through few-shot learning and retrieval-augmented generation. The authors highlight the value of the AI–human hybrid by working with a Fortune 500 food company and replicating a 2019 study using GPT-4. For their empirical work, they design system architecture and prompts to create personas, ask questions, and gather responses from synthetic respondents. They provide road maps for integrating LLMs into qualitative and quantitative marketing research and conclude that LLMs are valuable partners in generating insights.