Estudo de Preferências por Receitas do AllRecipes pelo Mundo
A considerable part of the culture and behavior of societies are derived from the habits and preferences built up over time. One representative characteristic that a group can present is the preference for certain food groups, thus, building the gastronomic identity of each region around the world. With the increasingly broad connections established by social networks, it is now more feasible to analyze such preferences on a large scale. This study examines recipes from Allrecipes.com network in three continents: America, Europe, and Asia. Based on the evaluations made by the users, a score was developed, allowing the separation of the recipes in two broad groups: well evaluated and poorly evaluated. All the ingredients of these recipes were extracted and used to assemble a network whose links were made via pointwise mutual information. This measure of association, used in pairs of ingredients, allowed us to find the main ingredients common to the countries. Our study may help to better understand the success, or otherwise, of a recipe, in a specific locality, based on its main ingredients. Thus, one of the main utilities envisioned for this work is to establish better recommendations for recipes.
A. Salvador, N. Hynes, Y. Aytar, J. Marin, F. Ofl i, I. Weber, and A. Torralba, “Learning cross-modal embeddings for cooking recipes and food images,” Training, vol. 720, no. 619-508, p. 2, 2017.
Y.-Y. Ahn, S. E. Ahnert, J. P. Bagrow, and A.-L. Barabási, “Flavor network and the principles of food pairing,” Scientifi c Reports, vol. 1, pp. 196 EP –, Dec 2011. Article.
T. Eftimov, G. Popovski, M. Petković, B. K. Seljak, and D. Kocev, “Covid-19 pandemic changes the food consumption patterns,” Trends in Food Science & Technology, vol. 104, pp. 268–272, 2020.
C.-Y. Teng, Y.-R. Lin, and L. A. Adamic, “Recipe recommendation using ingredient networks,” in Proceedings of the 4th Annual ACM Web Science Conference, WebSci’12, (New York, NY, USA), pp. 298–307, ACM, 2012.