MealRec$^+$: A Meal Recommendation Dataset with Meal-Course Affiliation for Personalization and Healthiness

TL;DR

MealRec^+ introduces a public benchmark dataset for meal recommendation with meal-course affiliation and healthiness information, addressing a long-standing data gap. The authors construct MealRec^+ by mapping course categories, simulating dining sessions, and expanding interactions via collaborative filtering, then scoring meals with FSA and WHO health standards. Through extensive baselines, they demonstrate that cooperative learning across user-course and user-meal interactions improves personalization, while healthiness can be nudged upward using post-filtering or contrastive techniques. The work highlights the importance of health-aware personalization in meal recommendations and provides a foundation for future AI-for-good food domain research with a publicly available resource on GitHub.

Abstract

Meal recommendation, as a typical health-related recommendation task, contains complex relationships between users, courses, and meals. Among them, meal-course affiliation associates user-meal and user-course interactions. However, an extensive literature review demonstrates that there is a lack of publicly available meal recommendation datasets including meal-course affiliation. Meal recommendation research has been constrained in exploring the impact of cooperation between two levels of interaction on personalization and healthiness. To pave the way for meal recommendation research, we introduce a new benchmark dataset called MealRec$^+$. Due to constraints related to user health privacy and meal scenario characteristics, the collection of data that includes both meal-course affiliation and two levels of interactions is impeded. Therefore, a simulation method is adopted to derive meal-course affiliation and user-meal interaction from the user's dining sessions simulated based on user-course interaction data. Then, two well-known nutritional standards are used to calculate the healthiness scores of meals. Moreover, we experiment with several baseline models, including separate and cooperative interaction learning methods. Our experiment demonstrates that cooperating the two levels of interaction in appropriate ways is beneficial for meal recommendations. Furthermore, in response to the less healthy recommendation phenomenon found in the experiment, we explore methods to enhance the healthiness of meal recommendations. The dataset is available on GitHub (https://github.com/WUT-IDEA/MealRecPlus).

Figures (4)

• Figure 1: (a) An example of three-course meals. (b) Complex relationships among users, courses, and meals.
• Figure 2: Different interaction learning methods.
• Figure 3: The nutrition data format of MealRec$^+$.
• Figure 4: Data distributions of datasets.