Related Experiment Video
Updated: May 28, 2025

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
Published on: August 16, 2024
The Potential Use of ChatGPT as a Sensory Evaluator of Chocolate Brownies: A Brief Case Study
1Department of Food Science and Human Nutrition, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA.
Abstract:
ChatGPT, a recently developed natural large language processing tool, has been widely explored in various fields of science and research. This study aimed to evaluate the potential use of ChatGPT as a sensory evaluator of hypothetical formulations of chocolate brownies. ChatGPT was prompted to act as an experienced taster to provide a detailed description of sensory characteristics for fifteen chocolate brownie formulations grouped into three categories (standard, common ingredients replacements, and uncommon ingredients replacements). Sentiment analysis, emotions/descriptors classification, and correspondence analysis were conducted to analyze ChatGPT responses. Results showed that the terms "trust", "anticipation", and "joy" were the most frequently expressed sentiments in the ChatGPT responses. The valence of all ChatGPT responses was mostly positive. The overall quality scores of all chocolate brownie formulations given by ChatGPT were extremely high, in the range of 8.5-9.5 (out of 10). ChatGPT tended to have higher positive emotions to formulations (some including worm meals and fish oil) that might have the opposite reactions with real consumers. Further research should focus on validating ChatGPT sensory descriptors with the outcomes of a human sensory panel. Additionally, future studies can explore the potential use of ChatGPT in evaluating the sensory characteristics of other food products for optimizing the product development process.

