# Of Wines and Reviews: Measuring and Modeling the Vivino Wine Social Network

**Authors:** Neema Kotonya, Paolo De Cristofaro, Emiliano De Cristofaro  
**arXiv:** [1804.10982](https://arxiv.org/abs/1804.10982)  
**Date:** 2018-04-29  
**Summary page:** https://www.summarizepaper.com/en/paper/1804.10982v3/

## Key points

- The paper "Of Wines and Reviews: Measuring and Modeling the Vivino Wine Social Network" analyzes social experiences surrounding wine consumption using data from Vivino, a social network for wine enthusiasts with over 26 million users worldwide.
- The study compares user perceptions of various wine types and regional styles across both New and Old World wines, examining them across price ranges, vintages, regions, varietals, and blends.
- Ratings provided by Vivino users are not biased by cost.
- Wine characteristics, language in wine reviews, and the distribution of wine ratings can be combined to develop prediction models.
- The paper provides valuable insights into the social experiences surrounding wine consumption through the lens of a large-scale social network.
- The findings have implications for both the wine industry and researchers interested in understanding consumer behavior in online communities.

## Summary

In their paper "Of Wines and Reviews: Measuring and Modeling the Vivino Wine Social Network," authors Neema Kotonya, Paolo De Cristofaro, and Emiliano De Cristofaro present a comprehensive analysis of social experiences surrounding wine consumption using data from Vivino, a social network for wine enthusiasts with over 26 million users worldwide. The study compares user perceptions of various wine types and regional styles across both New and Old World wines, examining them across price ranges, vintages, regions, varietals, and blends. One notable finding is that ratings provided by Vivino users are not biased by cost. The authors also explore how wine characteristics, language in wine reviews, and the distribution of wine ratings can be combined to develop prediction models. Specifically, they model user behavior to develop a regression model for predicting wine ratings and a classifier for determining user review preferences. Overall, this paper provides valuable insights into the social experiences surrounding wine consumption through the lens of a large-scale social network. The findings have implications for both the wine industry and researchers interested in understanding consumer behavior in online communities. This research offers an in-depth exploration of how different factors influence user ratings on Vivino's platform as well as how these insights can be used to inform decision making within the industry.