Sensory Evaluation of Foods Brownie Points for Chat GPT’s Food Analysis Skills

Can AI help decide which brownie recipe tastes best? A new study from the University of Illinois explores how ChatGPT could assist in food sensory evaluation — offering a faster, cost-effective tool for recipe development and product screening in the food industry.

AI is changing the way we work, create, and share information — but brownies? A new study from the University of Illinois Urbana-Champaign explores how Chat GPT can be used in the sensory evaluation of foods, specifically brownies. The study offers insights that could streamline development of new products, and possibly enhance recipes moving forward.

But, why use AI for brownie tasting? Most people would gladly line up to sample chocolatey treats. However, in the food industry, sensory evaluation is an essential yet rigorous and costly process. Companies rely on both trained human testers and consumer panels to assess key characteristics such as flavor, texture, and overall appeal before launching new products. Additionally, overcoming barriers such as human bias and sensory fatigue often proves challenging.

“Sometimes, relying on human testers can slow down the process, especially when multiple product prototypes need to be evaluated simultaneously. Sensory panels require time and careful coordination, and in some cases, certain ingredients may not be food-grade, making them unsuitable for tasting,” said study author Damir Torrico, assistant professor in the Department of Food Science and Human Nutrition, part of the College of Agricultural, Consumer and Environmental Sciences at Illinois. “That is why large language models such as Chat GPT are being considered for sensory evaluation. It is possible to create models that can replicate certain human responses.”

Torrico looked at fifteen different brownie recipes, ranging from standard ingredient lists to unusual combinations, including mealworm powder and fish oil. Torrico provided Chat GPT with recipe formulas, and asked the AI to describe sensory characteristics of each brownie, including taste, texture, and overall enjoyment. Torrico then categorized the themes of Chat GPT’s responses to determine if they were positive, negative, or neutral.

Surprisingly, Chat GPT’s responses were overwhelmingly positive, even for recipes that included unusual ingredients. This positivity aligns with the psychological phenomenon scientists call hedonic asymmetry. Hedonic asymmetry is the idea that people (and apparently AI) tend to describe things that are beneficial to them in more positive terms. Food serves a role in keeping us full and giving us energy, Torrico explains, causing humans to respond to food in a positive manner. In Chat GPT’s attempt to act human, it seemed to display this behavior.

“ChatGPT was trying to always see the good side of things,” Torrico said. He says that although kinks like hedonic asymmetry still need to be worked out, the study showcases the potential benefits of using AI in food development. Chat GPT could be used as a screening tool, helping food scientists narrow down recipe options before presenting them to a consumer panel. This could potentially save the industry time and money.

“Using AI can give general insights of what products can be considered for further testing, and what products shouldn’t be put through that long process,” Torrico said. “I could see Chat GPT being developed for sensory evaluation to help the industry.”

While Chat GPT may not be ready to steal your brownie, Torrico is excited about its potential. Looking ahead, he plans to refine the experiment, training Chat GPT to respond with a vocabulary that is similar to a human descriptive panel.

Original Article: “The Potential Use of ChatGPT as a Sensory Evaluator of Chocolate Brownies: A Brief Case Study,” is published in Foods [DOI: 10.3390/foods14030464] by Damir Torrico.

(ID:50371530)