Work

Quantifying Recipe Difficulty Based on Recipe Features

Year: 2026
Type: preprint
Abstract: Recipe-sharing sites have become widespread, and platforms such as Cookpad host millions of recipes; however, recipe difficulty is not specified. Therefore, it is difficult to select recipes that match their skill level. In this paper, we propose a computation method for quantifying recipe difficulty based on recipe details. The method comprehensively considers six features: cooking action level, the number of characters in the recipe, the number of cooking utensils, number of seasonings, number of ingredients, and number of steps. Each feature is normalized, and mutually correlated features are integrated using regression coefficients to avoid double-counting overlapping information. The validity of the proposed method is confirmed through a questionnaire survey with 30 respondents and verified by the Friedman test and four rank-distance metrics. The proposed method produces a strict total order over recipes, a property required for fine-grained recipe recommendation but not provided by single-feature baselines.
Language: English
Open Access status: green
OpenAlex ID: W7225920224
Cites: 10
Cited by:
Related to: 10