Wineinformatics : a new data science application / Bernard Chen.
Chen, Bernard.
2022
TP548
Available Online

Linked e-resources

Linked Resource Online Access
Concurrent users Unlimited
Authorized users Authorized users
Document Delivery Supplied Can lend chapters, not whole ebooks

Details

Title Wineinformatics : a new data science application / Bernard Chen.
Author Chen, Bernard.
ISBN 9789811973697 (electronic bk.)
9811973695 (electronic bk.)
9811973687
9789811973680
DOI https://doi.org/10.1007/978-981-19-7369-7
Publication Details Singapore : Springer, 2022.
Language English
Description 1 online resource.
Item Number 10.1007/978-981-19-7369-7 doi
Call Number TP548
Dewey Decimal Classification 641.22028563
Summary Wineinformatics is a new data science application with a focus on understanding wine through artificial intelligence. Thousands of new wine reviews are produced monthly, which benefits the understanding of wine through wine experts for winemakers and consumers. This book systematically investigates how to process human language format reviews and mine useful knowledge from a large volume of processed data. This book presents a human language processing tool named Computational Wine Wheel to process professional wine reviews and three novel Wineinformatics studies to analyze wine quality, price and reviewers. Through the lens of data science, the author demonstrates how the wine receives 90+ scores out of 100 points from Wine Spectator, how to predict a wines specific grade and price through wine reviews and how to rank a group of wine reviewers. The book also shows the advanced application of the Computational Wine Wheel to capture more information hidden in wine reviews and the possibility of extending the wheel to coffee, tea beer, sake and liquors. This book targets computer scientists, data scientists and wine industrial researchers, who are interested in Wineinformatics. Senior data science undergraduate and graduate students may also benefit from this book.
Bibliography, etc. Note References -- Chapter 3: Classification in Wineinformatics -- 3.1 Classification and Classification Label -- 3.2 Classification Algorithms -- 3.2.1 Support Vector Machines (SVM) -- 3.2.2 Naïve Bayes Classifier -- 3.3 Classification Evaluations -- 3.3.1 Fivefold Cross Validation -- 3.3.2 Evaluation Metrics -- 3.4 How Does a Wine Achieve 90+ Scores? -- 3.4.1 Dataset 1: The Big Dataset Results -- 3.4.2 Dataset 2: Twenty-First Century Bordeaux Dataset -- 3.4.3 Dataset 3: Twenty-First Century Elite Bordeaux -- References -- Chapter 4: Evaluation of Wine Judges -- 4.1 Wine Reviewers in Wine Spectator
Includes bibliographical references.
Access Note Access limited to authorized users.
Source of Description Online resource; title from PDF title page (SpringerLink, viewed December 12, 2022).
Series SpringerBriefs in computer science.
Available in Other Form Print version: 9789811973680
Linked Resources Online Access
Record Appears in Online Resources > Ebooks
All Resources
Intro
Preface
Contents
Chapter 1: Introduction
1.1 Data Science
1.2 Wineinformatics
1.3 Book Overview
References
Chapter 2: Data Collection and Preprocessing
2.1 Wine Sensory Reviews
2.2 Wine Spectator
2.3 Computational Wine Wheel
2.3.1 Wine Aroma Wheel
2.3.2 Bag of Words in Natural Language Processing
2.3.3 Development of the Computational Wine Wheel (CWW)
2.3.4 How to Use the CWW 2.0
2.4 Dataset
2.4.1 Dataset 1: The Big Dataset
2.4.2 Dataset 2: Twenty-First Century Bordeaux Dataset
2.4.3 Dataset 3: Twenty-First Century Elite Bordeaux

4.2 How to Evaluate Wine Reviewers
4.3 Ranking of the Wine Reviewers Using Naïve Bayes Classifier
4.4 Ranking of the Wine Reviewers Using SVM
4.5 Comparison of Naïve Bayes and SVM
References
Chapter 5: Regression in Wineinformatics
5.1 Regression Analysis Data
5.2 Methods
5.2.1 Support Vector Regression (SVR)
5.2.2 Evaluation Metrics
5.3 Regression Analysis
5.3.1 Can Wine Grade Be Predicted Through Their Reviews?
5.3.2 Can Wine Price Be Predicted Through Their Reviews?
References
Chapter 6: Multi-Class, Multi-Label and Multi-Target in Wineinformatics

6.1 Multi-Class, Multi-Label and Multi-Target
6.2 Wine Labels for Multi-Target Prediction
6.3 How to Predict Multi-Label and Multi-Target Problems?
6.3.1 Binary Relevance
6.3.2 Label Powerset
6.3.3 Classifier Chains
6.3.4 Bayesian Classifier Chains and Conditional Dependency Networks
6.4 Evaluation Metrics
6.5 Implementation of Multi-Label and Multi-Target in Wineinformatics
6.5.1 Apply Multi-Label on the Big Dataset
6.5.2 Apply Multi-Target on the Big Dataset
References
Chapter 7: Advanced Usage of the Computational Wine Wheel

7.1 Additional Information Captured by the Computational Wine Wheel
7.2 Naïve Bayes Classification Algorithm for Mixed Datatype
7.3 Does Additional Attributes Help?
7.3.1 Case Study on the Twenty-First Century Bordeaux Dataset
7.3.2 Case Study on the Twenty-First Century Elite Bordeaux Dataset
7.3.3 The More Attributes, the Better?
References
Chapter 8: Conclusion and Future Works
8.1 Conclusion
8.2 Future Works
References

Browse Subjects

Show more subjects...

Statistics

from
to
Export