Syrupy Mouthfeel and Hints of Chocolate -- Predicting Coffee Review Scores using Text Based Sentiment

TL;DR

This study leverages textual data from certified coffee reviews to develop regression models that accurately predict coffee scores, demonstrating the potential of sentiment analysis in specialized product rating predictions.

Contribution

It introduces a method to transform standardized coffee review texts into predictor spaces for accurate score prediction, a novel approach in coffee quality assessment.

Findings

Regression models accurately predict coffee scores

Textual sentiment features effectively capture quality patterns

Standardized reviews enable reliable score prediction

Abstract

This paper uses textual data contained in certified (q-graded) coffee reviews to predict corresponding scores on a scale from 0-100. By transforming this highly specialized and standardized textual data in a predictor space, we construct regression models which accurately capture the patterns in corresponding coffee bean scores.