Resource Intensity for Menu Items: How Much Land Is Required to Provide for Each Dish?
Abstract
In this study, we compute the Total Material Requirement (TMR) for dishes listed on popular cooking / recipe websites. TMR is an environmental index of a product representing the ultimate amount of raw extracted material necessary for producing a product. A high TMR equates to high mineral resource impact. In this study, we investigate the environmental impact of foods by calculating their TMR. food.com's website was used as the source of recipes. 500,231 recipe data were obtained and the recipes decomposed into ingredients: the average number of ingredients per recipe was 9 and the standard deviation was 4.03. The ingredients and their respective quantities were converted into TMR and summed for each recipe. From among the recipes, 19,305 were ultimately used after filtering them to ensure that more than 70% of ingredients of a recipe were available in our TMR dictionary. Finally, we computed averages for dish types such as "salad", "soup", "cakes", "pie", "bread", "cookies", "pasta", "muffin", "pudding", "pizza", and "stew", that were frequently used for recipe titles. As a result, we found that dishes using a larger amount of "butter" and "beef" have high mineral resource impact.
Cite
Text
Yamakata et al. "Resource Intensity for Menu Items: How Much Land Is Required to Provide for Each Dish?." International Joint Conference on Artificial Intelligence, 2018. doi:10.1145/3230519.3230585Markdown
[Yamakata et al. "Resource Intensity for Menu Items: How Much Land Is Required to Provide for Each Dish?." International Joint Conference on Artificial Intelligence, 2018.](https://mlanthology.org/ijcai/2018/yamakata2018ijcai-resource/) doi:10.1145/3230519.3230585BibTeX
@inproceedings{yamakata2018ijcai-resource,
title = {{Resource Intensity for Menu Items: How Much Land Is Required to Provide for Each Dish?}},
author = {Yamakata, Yoko and Yamasue, Eiji and McLellan, Benjamin and Aizawa, Kiyoharu},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2018},
pages = {15-20},
doi = {10.1145/3230519.3230585},
url = {https://mlanthology.org/ijcai/2018/yamakata2018ijcai-resource/}
}