If you savor jargon-enriched descriptions of iffy much-touted computer-involved approaches to using small amounts of data about things that are difficult to measure and interpret, this study may be of special interest:
“AI-driven prediction of consumer liking of coffee from sensory data,” Michael Gunning, Maite Pilar Serantes Laforgue, Jean-Xavier Guinard, and Ilias Tagkopoulos, npc Science of Food, 2026. The authors explain:
“This study presents a robust data analysis framework to deconstruct consumer preference using a dataset where 118 consumers rated their liking of 27 black drip coffee samples, the adequacy of select attributes on just-about-right (JAR) scales, and the sensory profile of the coffees with a check-all-that-apply (CATA) task. We integrated four feature-ranking methods to identify key sensory drivers, which informed the development of predictive models to forecast consumer liking.”
Bonus Study
If that study has stimulated your taste, do also sample a study titled “Comparison of Check-All-That-Apply (CATA), Rate-All-That-Apply (RATA), Flash Profile, Free Listing, and Conventional Descriptive Analysis for the Sensory Profiling of Sweet Pumpkin Porridge”.
