Quantifying Recipe Difficulty Based on Recipe Features

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.

Authors

Institutions

Publication Details

Journal
Research Square
Published
2026-11-12
DOI
https://doi.org/10.21203/rs.3.rs-11506878/v1
Primary Topic
Recommender Systems and Techniques
Type
preprint

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Quantifying Recipe Difficulty Based on Recipe Features

Masami Takata, Sae Okatani, Naoko Yoshii
Research Square
Recommender Systems and Techniques
preprint

Quantifying Recipe Difficulty Based on Recipe Features

Masami Takata, Sae Okatani, Naoko Yoshii
preprint en

Abstract

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.

Research Square
Nara Women's University (JP)
National Institute of Informatics
Recommender Systems and Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon