Can artificial intelligence convincingly answer consumer surveys? This project compares human responses with artificial intelligence generated responses produced both with and without respondent characteristics to understand how automated systems behave in survey research

Online surveys are widely used in sensory and consumer research to understand consumer perceptions, attitudes, and preferences. However, recent advances in artificial intelligence, particularly large language models, have introduced a growing risk that survey responses may be generated by automated systems rather than real participants.

This Master’s project aims to examine how responses generated by state-of-the-art large language models compare to verified human responses in consumer survey settings. The focus will be on differences in answering behaviour, response patterns, and language use across both rating-scale questions and open-ended responses.

The student will:

• Generate consumer survey responses using selected large language models both with and without predefined respondent characteristics.
• Compare artificial intelligence generated responses to human responses in terms of response behaviour and consistency across survey questions.
• Investigate whether providing artificial intelligence with respondent characteristics affects how it answers survey questions.
• Examine differences in how humans and artificial intelligence respond to open-ended questions.
• Explore whether artificial intelligence generated responses can be distinguished from human responses based on typical answering patterns in consumer surveys.

The project represents a scaled-down version of ongoing research on detecting artificial intelligence assisted survey fraud and contributes to improving data quality in sensory and consumer research conducted online.