By Topic

Using network analysis to understand the relation between cuisine and culture

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Dalwinderjeet Kaur Kular ; Department of Computer Science, Florida Institute of Technology, Melbourne, 32901, USA ; Ronaldo Menezes ; Eraldo Ribeiro

Cuisine is a key cultural component in all societies. The motto “we are what we eat” is known to most people; recently it has even been argued that “we are what we cook”. This paper delves into the complicated issue of trying to establish cultural communities based on recipes. Our hypothesis is that recipes and the ingredients of a recipe can tell us the origin of the people who prepared it. This approach could be used to define cultures not bounded by country borders but by similarities on how people prepare their food. In a more practical way, the understanding of relations between recipes can be used by automated recommendation systems in restaurants, supermarkets or be made available as an application to mobile devices. Our approach is based on Network Science. We have created a network were nodes represent a particular recipe, and edges connecting the nodes are defined based on ingredients shared by the nodes. We focused on ingredients because more classical recipes tend to prefer ingredients that are found locally-so the recipe captures a level of geo-dimension. After its creation, we evaluated the network of recipes (NoR) on the basis of topological properties. The measurements suggest that the NoR is a small-world network with scale-free properties. To delve into cultures we perform community analysis and correlate that with the ground truth available for each recipe (region or country of origin). Results suggest that in many cases one can derive the culture from the community structure alone.

Published in:

Network Science Workshop (NSW), 2011 IEEE

Date of Conference:

22-24 June 2011