Translating Sensory Perceptions: Existing and Emerging Methods of Collecting and Analyzing Flavor Data

Food flavor is hugely important in motivating food choice and eating behavior. Unfortunately for research and communication about flavor, many languages' flavor vocabularies are notoriously variable and must be aligned before data collection using training or after the fact by researchers. This dissertation demonstrates one example of each approach (conventional descriptive analysis (DA) and labeled free sorting, respectively), and compares their use to emerging, computational natural language processing (NLP) methods that use large volumes of existing text data. Rapid methods that align flavor vocabulary after data collection are most similar to NLP, and with the development or improvement of some strategic tools, NLP is well-poised to further accelerate the analysis of existing text data or unaligned vocabularies. DA, while much more time-consuming, ensures that the researchers, tasters, and readers have a shared definition of any flavor words used, an advantage that all existing rapid methods lack. With a greater understanding of how this differs from everyday communication about flavor, future researchers may be able to replicate this aspect of DA in novel descriptive methods.

This dissertation investigates the flavors of specialty beverages, specifically American whiskeys and cold brew coffees. American whiskeys differ from other whiskeys based on raw materials and aging practices, with the aging practices primarily setting them apart. While the most expensive American whiskeys are similar to Scotches and dominated by oaky, sultana-like flavors, only very rich consumers desire these flavors, with chocolate and caramel being the most widely preferred by most consumers. Degree of roasting has more of an impact on cold brew coffee flavor than the origin of the beans, and the coffee consumers surveyed here preferred dark roast to light roast cold brews.