From Words to Ratings: Machine Learning and NLP for Wine Reviews

Wine production is an important sector of the food industry in Bulgaria, contributing to both economic development and cultural heritage. The present study aims to show how natural language processing (NLP) and machine learning methods can be applied to analyze expert-written Bulgarian wine descript...

Full description

Saved in:
Bibliographic Details
Main Authors: Iliana Ilieva, Margarita Terziyska, Teofana Dimitrova
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Beverages
Subjects:
Online Access:https://www.mdpi.com/2306-5710/11/3/80
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849433791545737216
author Iliana Ilieva
Margarita Terziyska
Teofana Dimitrova
author_facet Iliana Ilieva
Margarita Terziyska
Teofana Dimitrova
author_sort Iliana Ilieva
collection DOAJ
description Wine production is an important sector of the food industry in Bulgaria, contributing to both economic development and cultural heritage. The present study aims to show how natural language processing (NLP) and machine learning methods can be applied to analyze expert-written Bulgarian wine descriptions and to extract patterns related to wine quality and style. Based on a bilingual dataset of reviews (in Bulgarian and English), semantic analysis, classification, regression and clustering models were used, which combine textual and structured data. The descriptions were transformed into numerical representations using a pre-trained language model (BERT), after which algorithms were used to predict style categories and ratings. Additional sentiment and segmentation analyses revealed differences between wine types, and clustering identified thematic structures in the expert language. The comparison between predefined styles and automatically derived clusters was evaluated using metrics such as Adjusted Rand Index (ARI) and Normalized Mutual Information (NMI). The resulting analysis shows that text descriptions contain valuable information that allows for automated wine profiling. These findings can be applied by a wide range of stakeholders—researchers, producers, retailers, and marketing specialists.
format Article
id doaj-art-c70cd8c7bf144b00a89561a10fdc6b97
institution Kabale University
issn 2306-5710
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Beverages
spelling doaj-art-c70cd8c7bf144b00a89561a10fdc6b972025-08-20T03:26:53ZengMDPI AGBeverages2306-57102025-06-011138010.3390/beverages11030080From Words to Ratings: Machine Learning and NLP for Wine ReviewsIliana Ilieva0Margarita Terziyska1Teofana Dimitrova2Faculty of Economics, University of Food Technologies, 4000 Plovdiv, BulgariaFaculty of Economics, University of Food Technologies, 4000 Plovdiv, BulgariaFaculty of Economic and Social Sciences, University of Plovdiv Paisii Hilendarski, 4000 Plovdiv, BulgariaWine production is an important sector of the food industry in Bulgaria, contributing to both economic development and cultural heritage. The present study aims to show how natural language processing (NLP) and machine learning methods can be applied to analyze expert-written Bulgarian wine descriptions and to extract patterns related to wine quality and style. Based on a bilingual dataset of reviews (in Bulgarian and English), semantic analysis, classification, regression and clustering models were used, which combine textual and structured data. The descriptions were transformed into numerical representations using a pre-trained language model (BERT), after which algorithms were used to predict style categories and ratings. Additional sentiment and segmentation analyses revealed differences between wine types, and clustering identified thematic structures in the expert language. The comparison between predefined styles and automatically derived clusters was evaluated using metrics such as Adjusted Rand Index (ARI) and Normalized Mutual Information (NMI). The resulting analysis shows that text descriptions contain valuable information that allows for automated wine profiling. These findings can be applied by a wide range of stakeholders—researchers, producers, retailers, and marketing specialists.https://www.mdpi.com/2306-5710/11/3/80wine reviewsnatural language processingmachine learningtext-based predictionwine style classification
spellingShingle Iliana Ilieva
Margarita Terziyska
Teofana Dimitrova
From Words to Ratings: Machine Learning and NLP for Wine Reviews
Beverages
wine reviews
natural language processing
machine learning
text-based prediction
wine style classification
title From Words to Ratings: Machine Learning and NLP for Wine Reviews
title_full From Words to Ratings: Machine Learning and NLP for Wine Reviews
title_fullStr From Words to Ratings: Machine Learning and NLP for Wine Reviews
title_full_unstemmed From Words to Ratings: Machine Learning and NLP for Wine Reviews
title_short From Words to Ratings: Machine Learning and NLP for Wine Reviews
title_sort from words to ratings machine learning and nlp for wine reviews
topic wine reviews
natural language processing
machine learning
text-based prediction
wine style classification
url https://www.mdpi.com/2306-5710/11/3/80
work_keys_str_mv AT ilianailieva fromwordstoratingsmachinelearningandnlpforwinereviews
AT margaritaterziyska fromwordstoratingsmachinelearningandnlpforwinereviews
AT teofanadimitrova fromwordstoratingsmachinelearningandnlpforwinereviews