Food Category Representatives: Extracting Categories from Meal Names in Food Recordings and Recipe Data

Abstract

FoodLog is a multimedia recording tool for producing food records for many individuals. In one year of operation, FoodLog has produced more than one million food records for meals eaten by users. We found nearly 70,000 unique food records among these data. In analyzing them, one of the challenges is to extract meal categories from such a large number of records. In this paper, we propose a method for compressing a meal name into a shorter representation. First, we collect similar meal names using a k-nearest neighbor search. Next, we construct a word graph to model the relationship between the meal names and items in the database. We select representative words by identifying minimal paths in the word graph. Finally, we obtain a few words that represent categorical information about the original meal name. We applied the method to data in food records for both FoodLog and the Rakuten Recipe database. Our results show that the method worked effectively for both datasets.

FoodLog: Multimedia Tool for Healthcare Applications

“…8 To create such food category representatives, food names (which, in Japanese, are generally compounded of a few words representing food items, cooking methods, and so on) were decomposed into words, and then each food name was grouped with food names of similar words. We made a word graph for the group, and the minimum path found was used as the representative.…”

Data Collection and Analysis of Usages from Connected Objects: Some Lessons

“…'Tomato' could thus be replaced by 'vegetable'. (see also [4,5]). In addition, ontologies allowed us also to add information, such as the type of diet implied by the use of some ingredient, or the type of course during the meal: entry, main course or dessert.…”