Wine Quality Prediction based on Chemical Components and Customer Reviews

Chinchwalkar, Swapnil Prakash (2023) Wine Quality Prediction based on Chemical Components and Customer Reviews. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (3MB) | Preview
Preview	PDF (Configuration manual) Download (14MB) | Preview

Abstract

Certification of food product quality is the primary priority of any nation. Each country’s inhabitants are advised to utilise products that guarantee quality assurance. The same approach is applicable to the wine segment. By examining the data set, it is possible to extract relevant information about the number of chemical elements in each wine and the opinions of each customer on those wines. In this study, multiple data mining classification methods, including SVC, Naive Bayes, Random Forest, Cat Boost, Gradient Boost, and Multi-layer Perceptron, are applied to the samples of different wines with their qualities necessary for quality certification. Similarly, the customer’s response after wine consumption along with their details are composed and with the help of VADER (Valence Aware Dictionary and Sentiment Reasoner) and BERT (Bidirectional Encoder Representations Transformers), the sentiments of the customer are determined. The wine with the best quality is recommended and the algorithms’ accuracy is compared. Furthermore, it is determined that the key elements impacting wine quality are volatile acidity, citric acid, alcohol, and sulphate. With varying feature sets, the accuracy is observed in the range of 78% to 88%. This research may be utilised not only as a guide for consumers but also as a resource for wine producers seeking to enhance wine quality.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Hasanuzzaman, Mohammed UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Food Industry > Beverage industry H Social Sciences > HF Commerce > Marketing > Consumer Behaviour
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	17 May 2023 14:38
Last Modified:	17 May 2023 14:38
URI:	https://norma.ncirl.ie/id/eprint/6576

Actions (login required)

View Item