Using Natural Language Processing to aid in descriptive analysis of whisky
August 16, 2021

Project Overview:
Applying Natural Language Processing (NLP) for keyword extraction from food reviews. This includes the investigation of whisky tasting notes and recipe ingredients.
CALS Strategic Priority(ies) that bes describes project goals:
Priority 1: Advance excellence in research, teaching and extension for the commonwealth and beyond
Priority 4: Ensure institutional excellence
BENEFICIARIES: sensory researchers, companies and consumers
TOOLS USED: Multiple sensory science researchers hand-label (annotate) words within a set of reviews as descriptors or non-descriptors. To do this, we developed a novel interactive tagging tool to label words within the reveiws as descriptors or non-descriptors. We then developed a deep learning model architecture that uses the labeled data to train a model to perform this keyword extraction. We then tested the model on other labeled whisky data and obtained very high accuracy.
ISSUE: How to effectively extract whisky descriptors from reviews. A descriptor is a word that describes certain aspects of a whisky (taste), e.g., smoke or fruity. This is challenging due to the unique nature of descriptors used for describing whiskies. Being able to extract descriptors from whisky reviews with known characteristics, such as origin, age, and price, will allow a one to predict such characteristics for new whiskies when only a text description is provided.
WHAT WAS DONE TO ADDRESS THIS ISSUE: In the project we use thousands of whisky reviews and human labeled reviews to train a deep learning model to recognize a food descriptor. The result is the ability to identify, with high probability, what is and is not a descriptor within free-form text describing food.
POTENTIAL IMPACTS: To date, we are unaware of other research that has applied Natural Language Processing techniques to this problem space. We foresee the ability to perform predictive analysis for aspects of a whisky just based on its tasting notes (descriptors) and ideally create "food language" models for use by other researchers.
Project Team:
- Chreston Miller
Data and Informatics Consultant, Engineering
University Libraries
chmille3@vt.edu - Jacob Lahne, Department of Food Science and Technology
- Leah Hamilton, PhD Candidate, Department of Food Science and Technology
- Michael Stamper, University Libraries
View more information about this project here: https://icat.vt.edu/projects/2019-2020/major/seeing-flavors.html
View our February 24 Lightning Talk to learn more from Jacob Lahne about this sensory topic.