Fusing Semantic, Lexical, and Domain Perspectives for Recipe Similarity Estimation

TL;DR

This paper presents a comprehensive approach to recipe similarity estimation by integrating semantic, lexical, and domain-specific features, validated through expert assessments, to enhance applications in personalized nutrition and automated recipe systems.

Contribution

It introduces a novel multi-perspective similarity framework combining ingredients, methods, and nutritional data, validated with expert input, advancing recipe comparison techniques.

Findings

Experts agreed on 80% of similarity assessments

Semantic and nutritional features are most influential

The method supports personalized diet and recipe automation

Abstract

This research focuses on developing advanced methods for assessing similarity between recipes by combining different sources of information and analytical approaches. We explore the semantic, lexical, and domain similarity of food recipes, evaluated through the analysis of ingredients, preparation methods, and nutritional attributes. A web-based interface was developed to allow domain experts to validate the combined similarity results. After evaluating 318 recipe pairs, experts agreed on 255 (80%). The evaluation of expert assessments enables the estimation of which similarity aspects--lexical, semantic, or nutritional--are most influential in expert decision-making. The application of these methods has broad implications in the food industry and supports the development of personalized diets, nutrition recommendations, and automated recipe generation systems.