The study published in the journal ‘Physiology & Behaviour’ analysed nearly 400,000 food reviews posted by Amazon customers to analyse and look into the food choices people make and like these days.
“This is the first study of this scale to study food choice beyond the artificial constraints of the laboratory. Sweet was the most frequently mentioned taste quality and the reviewers definitively told us that human food is over-sweetened,” said Danielle Reed, the study’s lead author.
The study used data posted on an open-source data science site to examine 393,568 unique food reviews of 67,553 products posted by 256,043 Amazon customers over a 10-year period. The scientists computed the number of reviews looking into categories of taste, texture, odour, spiciness, cost, health, and customer service.
“Reading and synthesising almost 400,000 reviews would essentially be impossible for a human team, but recent developments in machine learning gave us the ability to understand both which words are present and also their underlying semantic meaning,” said Joel Mainland, the study’s co-author.
When looking at reviews that referred to sweet taste, the researchers found that over-sweetness was mentioned 25 times more than under-sweetness.
They identified two factors that tended to account for polarising 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.
“Genetic differences in taste or olfactory receptor sensitivity may help account for the extreme reactions that some products get,” said Reed. “Looking at the responses to polarising foods could be a way to increase understanding of the biology of personal differences in food choice,’ added Reed.
Together, 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.
(with agency inputs)