Advances in Agriculture and Food Research: GPT's Capabilities in Consumer Food Survey Analysis

Strategic Insights -

Recent research in Beijing, People's Republic of China, has explored the application of Generative Pre-trained Transformer (GPT) models in automating consumer food survey analysis. The study, led by Chinese Academy of Agricultural Sciences researchers, examined Chinese consumers' acceptance of plant-based foods, cultured meat, insect-based proteins, and microbial proteins. The research found that traditional survey analysis methods face limitations in handling large-scale, open-ended responses, whereas GPT's natural language processing capabilities offer efficient and bias-reduced alternatives.

Key Takeaways:

  • The study employed Partial Least Squares Structural Equation Modeling (PLS-SEM) to investigate the effects of food technophobia and food values on consumer acceptance of alternative proteins.
  • Results showed that acceptance is highest for plant-based foods and lowest for cultured meat, with perceived benefits and perceived risks impacting consumer willingness to adopt these foods.
  • Mediation analysis revealed that attitudes toward food safety, naturalness, and production processes shape consumer choices.
  • The findings underscore the value of using GPT for comprehensive, real-time survey analysis.
  • Marketing strategies and policies that emphasize product safety, environmental benefits, and consumer education may enhance acceptance of alternative proteins.
  • The study underscores the potential of GPT in automating consumer food survey analysis, offering a more efficient and bias-reduced approach.
  • The research highlights the importance of understanding consumer attitudes toward food safety, naturalness, and production processes in shaping acceptance of alternative proteins.

Statistics:

  • The study analyzed data from a large-scale consumer survey, examining Chinese consumers' acceptance of plant-based foods, cultured meat, insect-based proteins, and microbial proteins.
  • Results showed that 73.4% of respondents were willing to try plant-based foods, while 21.1% were willing to try cultured meat.
  • Perceived benefits (PB) and perceived risks (PR) were found to positively and negatively impact consumer willingness, respectively.
  • 56.2% of respondents reported being concerned about food safety, while 43.8% reported being concerned about the environmental impact of food production.

Sources:

  • Assessing GPT's capabilities in consumer food survey analysis: A comparative approach for understanding food technophobia and novel protein perceptions. Journal of Agriculture and Food Research, 2025,22():102086.
  • Chinese Academy of Agricultural Sciences
  • Institute of Food Science and Technology, Chinese Academy of Agricultural Sciences. Peihua Ma, Si Chen, Wenfan Su, Jiping Sheng, Xiaoxue Jia, Cheng-I Wei, Yunbo Luo, Jiao Xu, Yan Song, Ling Yong, Tong Ou, Ying Yue.
  • DOI: https://doi-org.sdpl.idm.oclc.org/10.1016/j.jafr.2025.102086.