Ranking Recipes According to Classicality towards Understanding Evolution of Food Preference

Food evolution has been a revealing indicator of human beings´ living activities. Knowing how food and people´s food preferences evolve helps us to elucidate important aspects of human society, culture, and history. Before, an individual researcher was able to track changes of food by manual investigation of recipes in books or among people. Propagation of information among common people was slow, usually limited to being narrow and regional. Today, people can upload their own recipes easily to recipe sites such as CookPad in Japan. Information related to food has increased rapidly. Therefore, tracking food evolution has become impossible without computer-based data analysis. To help elucidate the evolution of food preferences, we propose a novel measure, called the classicality score, of a recipe, and propose a method for computing the score by analyzing recipe data including characteristics of the ingredients of each recipe. Using recipe data of several foods on CookPad, we examined the usefulness of our proposal by comparing rankings according to our classicality score to those according to other measures. Some interesting discoveries were made from case studies of the rankings.