Estimating Glycemic Impact of Cooking Recipes via Online Crowdsourcing and Machine Learning

TL;DR

This paper presents a novel data-driven method combining online crowdsourcing and machine learning to estimate the glycemic impact of recipes, offering a cost-effective alternative to laboratory testing for dietary health assessment.

Contribution

It introduces a new approach that leverages crowdsourced data and machine learning to accurately predict recipe glycemic impact, addressing limitations of existing healthiness metrics.

Findings

The best classification model achieved high accuracy in identifying unhealthful recipes for diabetics.

Crowdsourced data from Amazon Mechanical Turk effectively trained the model.

Traditional healthiness metrics may not reliably indicate glycemic impact.

Abstract

Consumption of diets with low glycemic impact is highly recommended for diabetics and pre-diabetics as it helps maintain their blood glucose levels. However, laboratory analysis of dietary glycemic potency is time-consuming and expensive. In this paper, we explore a data-driven approach utilizing online crowdsourcing and machine learning to estimate the glycemic impact of cooking recipes. We show that a commonly used healthiness metric may not always be effective in determining recipes suitable for diabetics, thus emphasizing the importance of the glycemic-impact estimation task. Our best classification model, trained on nutritional and crowdsourced data obtained from Amazon Mechanical Turk (AMT), can accurately identify recipes which are unhealthful for diabetics.