Modelling the sensory space of varietal wines: Mining of large, unstructured text data and visualisation of style patterns

The increasingly large volumes of publicly available sensory descriptions of wine raises the question whether this source of data can be mined to extract meaningful domain-specific information about the sensory properties of wine. We introduce a novel application of formal concept lattices, in combination with traditional statistical tests, to visualise the sensory attributes of a big data set of some 7,000 Chenin blanc and Sauvignon blanc wines. Complexity was identified as an important driver of style in hereto uncharacterised Chenin blanc, and the sensory cues for specific styles were identified. This is the first study to apply these methods for the purpose of identifying styles within varietal wines. More generally, our interactive data visualisation and mining driven approach opens up new investigations towards better understanding of the complex field of sensory science.

[1]  John Elder,et al.  Practical Text Mining and Statistical Analysis for Non-structured Text Data Applications , 2012 .

[2]  S. Buratti,et al.  Characterization and classification of Italian Barbera wines by using an electronic nose and an amperometric electronic tongue , 2004 .

[3]  Dong-Bin Shin,et al.  A study on concepts and utilization of Geo-Spatial Big Data in South Korea , 2016 .

[4]  Jerzy Krysiński,et al.  A data mining approach to optimize pellets manufacturing process based on a decision tree algorithm. , 2015, European journal of pharmaceutical sciences : official journal of the European Federation for Pharmaceutical Sciences.

[5]  W. D. Toit,et al.  A comprehensive review on Sauvignon blanc aroma with a focus on certain positive volatile thiols , 2012 .

[6]  Zahid Anwar,et al.  Data mining techniques and applications — A decade review , 2017, 2017 23rd International Conference on Automation and Computing (ICAC).

[7]  Ganesh Bagler,et al.  Analysis of Food Pairing in Regional Cuisines of India , 2015, PloS one.

[8]  Mónica Bécue-Bertaut,et al.  An original methodology for the analysis and interpretation of word-count based methods: Multiple factor analysis for contingency tables complemented by consensual words , 2014 .

[9]  Sebastian E Ahnert,et al.  Network analysis and data mining in food science: the emergence of computational gastronomy , 2013, Flavour.

[10]  Bernhard Ganter,et al.  Formal Concept Analysis: Mathematical Foundations , 1998 .

[11]  Gastón Ares,et al.  Comparison of Correspondence Analysis based on Hellinger and chi-square distances to obtain sensory spaces from check-all-that-apply (CATA) questions , 2015 .

[12]  K. Héberger,et al.  Supervised pattern recognition in food analysis. , 2007, Journal of chromatography. A.

[13]  Brian A. Davey,et al.  An Introduction to Lattices and Order , 1989 .

[14]  Brian A. Davey,et al.  Introduction to Lattices and Order: Frontmatter , 2002 .

[15]  Fritz Venter,et al.  Using a Lattice for Visual Analysis of Categorical Data , 1995, Perceptual Issues in Visualization.

[16]  L. V. Antwerpen.  Chemical and Sensory profiling of dry and semi-dry South African Chenin blanc wines , 2012 .

[17]  Evette Hanekom.  Chemical, sensory and consumer profiling of a selection of South African Chenin blanc wines produced from bush vines , 2012 .

[18]  Pascal Schlich,et al.  Correspondence analysis in sensory evaluation , 1991 .

[19]  Bernard Chen,et al.  Wineinformatics: Applying Data Mining on Wine Sensory Reviews Processed by the Computational Wine Wheel , 2014, 2014 IEEE International Conference on Data Mining Workshop.

[20]  I. Pretorius,et al.  The Use of Candida pulcherrima in Combination with Saccharomyces cerevisiae for the Production of Chenin blanc Wine , 2003 .

[21]  C. Paradis,et al.  Describing Sensory Experience: The Genre of Wine Reviews , 2013 .

[22]  G. D. Oosthuizen,et al.  Knowledge discovery in databases using lattices , 1997 .

[23]  Mónica Bécue-Bertaut,et al.  Tracking verbal-based methods beyond conventional descriptive analysis in food science bibliography. A statistical approach , 2014 .

[24]  Harry T. Lawless,et al.  Multidimensional scaling of sorting data applied to cheese perception , 1995 .

[25]  Paulo Cortez,et al.  Modeling wine preferences by data mining from physicochemical properties , 2009, Decis. Support Syst..

[26]  Brian A. Davey,et al.  Introduction to Lattices and Order: Preface to the second edition , 2002 .

[27]  Shu-Hsien Liao,et al.  Data mining techniques and applications - A decade review from 2000 to 2011 , 2012, Expert Syst. Appl..

[28]  Albert-László Barabási,et al.  Flavor network and the principles of food pairing , 2011, Scientific reports.

[29]  R. A. Arnold,et al.  Progress Towards a Standardized System of Wine Aroma Terminology , 1984, American Journal of Enology and Viticulture.

[30]  Aida Mustapha,et al.  Classification-based Data Mining Approach for Quality Control in Wine Production , 2012 .

[31]  Susan E.P. Bastian,et al.  Multidimensional scaling (MDS), cluster and descriptive analyses provide preliminary insights into Australian Shiraz wine regional characteristics , 2013 .

[32]  E. Beh,et al.  A European perception of food using two methods of correspondence analysis , 2011 .

[33]  K. Geoffrey White,et al.  The distinctive flavour of New Zealand Sauvignon blanc: Sensory characterisation by wine professionals , 2007 .

[34]  E. King,et al.  Classical descriptive analysis , 2014 .

[35]  Amir Etemad-Shahidi,et al.  An alternative approach for the prediction of significant wave heights based on classification and regression trees , 2008 .

[36]  Muna S. Al-Razgan,et al.  Exploring the Food Pairing Hypothesis in Arab Cuisine: A Study in Computational Gastronomy , 2016 .

[37]  Walter J. Freeman,et al.  Classification of EEG Spatial Patterns with a Tree-Structured Methodology: CART , 1986, IEEE Transactions on Biomedical Engineering.

[38]  I. S. Pretorius,et al.  The effect of multiple yeasts co-inoculations on Sauvignon Blanc wine aroma composition, sensory properties and consumer preference , 2010 .

[39]  Lamiaa Fattouh Ibrahim,et al.  Text Mining and Knowledge Discovery from Big Data: Challenges and Promise , 2016 .

[40]  S. Carlin,et al.  Untangling the wine metabolome by combining untargeted SPME–GCxGC-TOF-MS and sensory analysis to profile Sauvignon blanc co-fermented with seven different yeasts , 2016, Metabolomics.