As community-based recipe platforms continue to grow in popularity, recipe recommendation is an active research area. Simultaneously, the analysis of online recipes can provide us with insights on dietary patterns in particular communities. In this paper, we focus on recipe recommendation for a user group that is constrained in terms of choices: diabetes patients need to balance their diet more than average persons and to be aware of the nutritional value of their meals. First, we discuss the type of situations where diabetes-speci c food recommendations are desirable. Further, we analyze how people's age and gender interact with food intake. Based on a large dataset, we explore how variations in `canonical meals' can be exploited for recommending which alternatives better t the user's dietary requirements.
Diabetes is a widely spread chronic disease that a ects about 10% of the Western population. Patients su ering from diabetes have to take many vital decisions on a daily basis, including: am I allowed to eat this, what is my blood sugar level, how much insulin should I take right now? Particularly those who have just been diagnosed with diabetes experience di culties facing such decisions.
The GlycoRec project1 aims to develop a system that provides diabetes patients with personalized support and advices for improving their everyday lives. GlycoRec will provide patients with information and advice regarding their nutrition, physical activities, and the use of medicine. This empowers patients to better communicate their needs with their doctors and advisors, and to better implement advices and stated goals in their everyday lives.
In this paper, we present our rst steps towards personalized nutritional advice. Despite the availability of online nutritional information2, these databases only provide information on single ingredients and/or standardized products such as ready-made meals. Our goal is to provide diabetes patients with recommendations and feedback in everyday situations, including: (i) How many 1 https://www.pfh.de/hochschule/forschung/forschungsprojekt-glycorec.html 2 The quality and acceptance of databases with nutritional information vary wildly.
In Germany, an established resource is http://www.mri.bund.de/de/service/ datenbanken/bundeslebensmittelschluessel.html. carbohydrates can I expect that the Thai curry on the menu contains?, and (ii) Which recipe variation best matches both my dietary restrictions and my taste?
Based on an extensive dataset from the German recipe website Kochbar.de3, we show that there are di erences in eating patterns with respect to gender, age group, and dietary restrictions, such as diabetes. We cluster popular meal names into `canonical meals ' and analyze to what extent these meals vary in terms of ingredients and nutritional value. These insights provide directions for strategies to nd the best recipe or for adapting recipes to user needs and preferences. 2
Diabetes mellitus is a widespread disease that requires constant attention of
the patients and their caregivers. Research has shown that e ective prevention
of diabetes-related complications includes lifestyle changes that include an
increased physical activity as well as a diet that is associated with lower blood
pressure [
Online recipe recommenders can play an important role in generating healthy
meal plans. Even though the used ingredients are the major reason for liking or
disliking a meal, there are health-conscious users who also take nutritional
information into account [
An in-depth analysis on how users choose and adapt recipes is given by Teng
et al [
Kusmierczyk et al. analyzed data from the German community platform
Kochbar and found clear seasonal and weekly trends in online food recipe
production, both in terms of nutritional value (fat, proteins, carbohydrates and
calories) [
Making use of these and other insights, the team from IBM Watson created
the prototype Chef Watson, which automatically creates recipes that match user
preferences, based on existing recipes from the Bon Appetit recipe website [
We use a crawl from Kochbar.de, a German online food community website to
which users can upload and rate cooking recipes, provided by Kusmierczyk et
3 https://www.kochbar.de
al. [
We consider only the 309 thousand recipes that contain valid information on energy (in kJ and kcal), carbohydrates, proteins, and fat. For each recipe, a mostly structured list of ingredients (with quantities) is given. We extracted the ingredients and performed simple normalization by converting the text to lowercase, normalizing whitespaces, removing text in parentheses, and splitting on conjunctions such as \and" and \or". This process yields more than 300 thousand ingredients, with an average of 10 ingredients per recipe. As only a moderate amount of 2258 ingredients occurs frequently (in at least 100 recipes), this simple preprocessing is su cient for a rst analysis of the dataset. 4
As a rst step, we aim to identify di erences in user recipes created by di erent user groups. Among the 200 thousand users, 95 thousand provided information regarding gender (25 thousand male, 70 thousand female users) and 57 thousand provided information regarding their age (mean 42.2, median 42). In addition, we are interested in diabetes patients. However, apparently most patients did not disclose the fact that they su er from diabetes: from the pro le information we are able to identify only 65 users who su er from diabetes or have close relatives with diabetes - a number too small for an e ective analysis. Similarly, only about 3.000 of the recipes have been labeled as `diabetes friendly'. By contrast, about 220.000 recipes are marked as gluten free, 137.000 as lactose free and (only) 37.000 recipes as vegetarian.
30 ]g0 25 0 1 [/g 20 s t iren 15 t u N gea 10 r e vA 5 carbohydrates
fat proteins [10, 20) [20,30) [30, 40) [40, 50) [50, 60) [60, 70) [70, 80]
User Age
As discussed by [
Karto elsalat (potato salad) 1,863 Pizza 1,812 Kasekuchen (cheese cake) 1,681 Apfelkuchen (apple pie) 1,450 Gulasch (gulash) 1,187 Nudelsalat (pasta salad) 1,706 Eierlikor (egg liquor) 1,085 Pfannkuchen (pancake) 1,221 Lasagne (lasagna) 1,187 Tiramisu 1,358 41,226 38,250 36,807 34,935 28,668 30,196 27,482 24,492 22,570 22,931 14,117 13,210 12,085 11,982 10,162 9,782 9,360 8,550 8,034 7,773
To nd out to what extent canonical meals vary in nutritional value, we selected three di erent, representative meals and calculated the means and standard deviations - see Table 2. We also analyzed which ingredients are associated with recipes that are high and low in carbohydrates, fat, proteins, and energy by calculating the average levels for all meals and sorting them accordingly.
Potato salad is low in protein, but the standard deviations are relatively high. Ingredients associated with high protein are meat and sh, low-protein recipes contain vegetables instead, such as pickles, radish, olives and asparagus. The same pattern can be found for lasagna. Low-fat cheese cake is associated with low-fat milk products and high-fat with chocolate and cream cheese.
Cheese cake Lasagna Carbohydrates Fat
Mean Std dev
8:44 8.025 15.68 10.81 13:09 11:97 13:23 17.64 9.29 11.00 3:27 7:32 8:06 3.60 2.97 6.18
These ndings con rm our expectation that it is possible to estimate the nutritional value of certain dishes from the recipes associated with these dishes and that one can identify ingredients associated with high or low levels of food value. This provides a good base for developing food recommender systems that suggest `better recipes' and alternative ingredients for particular recipes. Existing food databases for diabetes patients are incomplete and inconsistent. Moreover, they only contain ingredients and standardized products. Diabetes patients typically learn over time what they can eat and what not, but this is often not su cient for many common situations. In restaurants, served meals are often `black boxes' in terms of nutritional value, which causes great uncertainty among diabetes patients, especially when trying out new meals while on vacation in foreign countries.
To provide patients with advice and information on the nutritional value of a meal - and to recommend them alternative meals or ingredients - we aim to exploit recipe sites such as Kochbar.de, which contain user-provided recipes. This paper provides some rst insights and con rms the feasibility of the approach.
A particular challenge for the food recommender will be to provide detailed feedback on the precision of its estimations and the resulting recommendations. Particularly for `canonical meals' with many variations, estimations may need to be re ned with additional user input and feedback.
The GlycoRec project is funded by the Federal Ministry of Education and Research (BMBF) under the funding scheme Adaptive, Learning Systems (Adaptive, lernende Systeme).