Identifying Ingredient Substitutions Using a Knowledge Graph of Food

Abstract

People can affect change in their eating patterns by substituting ingredients in recipes. Such substitutions may be motivated by specific goals, like modifying the intake of a specific nutrient or avoiding a particular category of ingredients. Determining how to modify a recipe can be difficult because people need to 1) identify which ingredients can act as valid replacements for the original and 2) figure out whether the substitution is “good” for their particular context, which may consider factors such as allergies, nutritional contents of individual ingredients, and other dietary restrictions. We propose an approach to leverage both explicit semantic information about ingredients, encapsulated in a knowledge graph of food, and implicit semantics, captured through word embeddings, to develop a substitutability heuristic to rank plausible substitute options automatically. Our proposed system also helps determine which ingredient substitution options are “healthy” using nutritional information and food classification constraints. We evaluate our substitutability heuristic, diet-improvement ingredient substitutability heuristic (DIISH), using a dataset of ground-truth substitutions scraped from ingredient substitution guides and user reviews of recipes, demonstrating that our approach can help reduce the human effort required to make recipes more suitable for specific dietary needs.

A comprehensive survey of personal knowledge graphs

“…This makes it a very viable environment for maintaining a PKG for each patient. PKGs can be used to make personalized diet and lifestyle plans for patients suffering from chronic diseases such as diabetes (Shirai et al, 2021) by taking their various allergies and eating habits into account and integrating that knowledge with other domain‐specific KGs like FoodKG (Haussmann et al, 2019). This would make the diet plan truly personalized as a diet endorsed to be healthy and efficient for one patient might not be the same for another, due to the differences in their health conditions and also their treatment styles.…”

Applications of knowledge graphs for food science and industry

“…For existing recipes, we can resort to food knowledge graphs to find various alternative ingredients under requirements or develop new flavors. 81 , 92 Also we can develop novel culinary recipes, including not only their ingredient combinations but also their ingredient proportions and time durations of each step via combining the constructed food knowledge graph and mathematical models. 93…”

Food Recipe Ingredient Substitution Ontology Design Pattern

“…(see Figure 1). The problem of substitution has been analyzed in more detail by Shirai et al [10]. The authors have defined the objective of finding and ranking substitutes in the contexts of two motivating cases: (1) personal dietary restrictions satisfaction and (2) modification of the nutritional contents of meals.…”

“…Recipe adaptations were performed by searching for recipes that most closely matched a given user query and then performing modifications based on ingredient taxonomy similarity and substitution rules. Shirai et al [10] coupled explicit semantic information with implicit information (embeddings) to create the DIISH heuristic for ingredient substitutability, which provides substitutes depending on user context linked to health.…”