General funding from the Ambrose Monell Foundation supports many Monell Center endeavors, including some that are seemingly small. One example is R-Club, a weekly meeting of Center scientists devoted to R, a statistical computing and programming language that is widely used in big data analysis, including machine learning and artificial intelligence. Founded in March 2016, that dedicated time for weekly discussion and knowledge sharing is now paying off in big ways to advance the growing field of sensory nutrition.
A recent study from the Monell Center analyzed nearly 400,000 food reviews posted by Amazon customers to gain real-world insight into the reasons behind the food choices that people make. The findings highlight the critical role of sensory factors in driving food choice, with taste ranking ahead of price, health, and convenience as the issue most discussed.
“This is the first study of this scale to examine how and what humans write about food and gave us a golden opportunity to study people beyond the artificial constraints of the laboratory,” said study leader and behavioral geneticist Danielle Reed, PhD.
“The results point firmly to taste as the central reason that people eat what they do, telling us that treatments for obesity and other diseases must take sensory factors, including the drive for ‘good taste,’ into account if they are to succeed.”
Based on an open-source data set of Amazon product reviews, the study first used a sophisticated language-processing program to identify words related to taste, texture, odor, spiciness, cost, health, and customer service in 393,568 unique food reviews of 67,553 products posted by 256,043 customers over a 10-year period. The scientists then used customized R programs to analyze the reviews that mentioned each of these categories.
The focus on product over-sweetness was striking, as almost one percent of the product reviews, regardless of food type, used the phrase “too sweet.” When looking at reviews that referred to sweet taste, the researchers found that over-sweetness was mentioned 25 times more than under-sweetness.
“Sweet was the most frequently mentioned taste quality and the reviewers definitively told us that human food is over-sweetened,” said Reed.
Interestingly, saltiness was rarely mentioned, a somewhat surprising finding in light of public health concerns about excess sodium consumption.
Seeking to better understand individual differences in how people respond to a given food, the scientists also looked at responses to the 10 products that received the widest range of ratings, as defined by the variability in the number of stars the product received.
They found that two factors tended to account for ‘polarizing reviews’ related to a product: product reformulation and differing perspectives on the product’s taste. With regard to taste, people often rated the sweetness of a product differently. Response to a product’s smell also contributed to differences in opinion about a particular product. The team suspects that these extreme sensory responses may reflect genetically-based differences in taste or smell sensitivity.
Advancing Sensory Nutrition
The findings illustrate the potential uses of big-data approaches and consumer reviews to advance sensory nutrition, an emerging field that integrates knowledge from sensory science with nutrition and dietetics to improve health. Moving forward, similar methods may inform approaches to personalized nutrition that can match a person’s sensory responses to inform healthier food choices.