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

2026-03-10

AI Summary

This work proposes a multidimensional approach to recipe similarity assessment that integrates semantic, lexical, and nutritional dimensions to comprehensively analyze ingredients, cooking methods, and nutritional attributes. Leveraging natural language processing and semantic similarity computation, the authors construct a model and design an expert evaluation interface to quantify the relative contribution of each dimension to human similarity judgments. This study represents the first systematic integration of these three dimensions, achieving 80% agreement among domain experts across 318 recipe pairs. The findings demonstrate that both nutritional content and semantic information significantly influence expert assessments of recipe similarity, thereby offering a theoretically grounded and practically applicable framework for personalized dietary recommendation systems and automated recipe generation.

Technology Category

• Natural Language Processing: Lexical Semantics and Morphology
• Application Domains: Humanities & Computational Social Science
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

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.

Problem

• recipe similarity
• semantic similarity
• lexical similarity
• nutritional attributes
• food domain

Innovation

• recipe similarity
• semantic similarity
• lexical similarity
• nutritional attributes
• multi-perspective fusion