JMIR Publications

Background:

Dietary management is critical to maintaining human health. Social media platforms are widely used for daily recording and communication for individuals’ diets, activities, and emotions. These social media texts and images are valuable resources for dietary management.

Objective:

We developed iFood, an applet providing personal dietary management based on social media data. The seamless connection between iFood and social media enabled the efficient personal dietary management.

Methods:

We developed iFood, which consists of 7 key components: a social media data collector, a diet information collector, a diet image identifier, a text extractor, a visual-textual data integrator, a nutrient calculator, and a dietary report generator. These components were used to collect data, extract diet entities, recognize diet, fuse unimodality data, calculate nutrient intake, and generate dietary reports via a WeChat applet.

Results:

We obtained 105,227 dietary textual records and 407,133 diet images from 96 users on Weibo. After applying machine learning algorithms to integrate the identification results of texts and images, we obtained 1,286 diets images and information with the visual-textual integrator accuracy of 51.38%. Nutrient intake, diet category distribution, and diet records were displayed through the iFood applet on a daily, weekly, monthly, and yearly basis.

Conclusions:

Our research involved the creation of a dietary management application called iFood, which is based on social media. We conducted experiments to evaluate the efficacy of this app in maintaining personal dietary management. Our results show that iFood is an effective tool for managing individual dietary behaviors through its seamless integration with social media data and accurate analysis capabilities. This study suggests that future products could utilize social media data to promote healthy lifestyles.

Clinicaltrial: