Fabrício Goulart , Voltaire Sant’Anna , Valérie L. Almli , Gabriel Tolotti Maschio
{"title":"Can children and artificial intelligence be sources of ideas for school meal preparations based on whole food utilization?","authors":"Fabrício Goulart , Voltaire Sant’Anna , Valérie L. Almli , Gabriel Tolotti Maschio","doi":"10.1016/j.foodqual.2024.105349","DOIUrl":null,"url":null,"abstract":"<div><div>Involving children in creation of school meals is important to engage them on healthy and sustainable eating habits, and the whole food utilization is a way to avoid food waste and increase the consumption of nutrients. Also, artificial intelligence (AI) has shown to be an interesting source of new ideas but has not been used for designing children’s meals. The aims of the work were to evaluate the potential of school meals either co-designed by children or generated with AI, and to explore parents’ perception towards the utilization of whole food in their children’s meal. Children, with the potential support of their parents, proposed recipes with whole fruit/vegetable utilization, and a selection among the suggestions was conducted by nutritionists and the school cooks. The selected meal was compared to a similar recipe from ChatGPT generated from a simple prompt with regard to their acceptance and emotions evoked. The two dishes were variations of carrot pie recipes including vegetable peel and were both prepared by experienced school cooks. A third recipe proposed by the school’s cooks was used as comparison. Parents’ perceptions towards whole food utilization to their children were elicited by sentence completion methodology. Results showed that children liked both their and the cooks’ recipes but rejected ChatGPT’s recipe. Both cooks’ and children’s carrot pies evoked positive emoji pairs, meanwhile ChatGPT’s carrot pie was associated to emojis of negative connotation. Texture and unfamiliar taste were cited to justify the rejection. For parents, the utilization of whole fruits/vegetable in children’s meals is perceived as a good and nutritious idea, but safety concerns were revealed. This work demonstrates co-design with school children and whole food utilization as actionable strategies towards reducing waste of nutritious resources. Moreover, the study reports an unsuccessful exploratory usage of ChatGPT through a task-focused prompt. This may suggest the importance of specifying the context of the task when prompting an AI, to compensate for contextual information that is implicitly available to humans. Concerns about safety aspects should be addressed to ensure parents’ support for whole vegetable utilization in school meals.</div></div>","PeriodicalId":322,"journal":{"name":"Food Quality and Preference","volume":"123 ","pages":"Article 105349"},"PeriodicalIF":4.9000,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Food Quality and Preference","FirstCategoryId":"97","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0950329324002519","RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"FOOD SCIENCE & TECHNOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Involving children in creation of school meals is important to engage them on healthy and sustainable eating habits, and the whole food utilization is a way to avoid food waste and increase the consumption of nutrients. Also, artificial intelligence (AI) has shown to be an interesting source of new ideas but has not been used for designing children’s meals. The aims of the work were to evaluate the potential of school meals either co-designed by children or generated with AI, and to explore parents’ perception towards the utilization of whole food in their children’s meal. Children, with the potential support of their parents, proposed recipes with whole fruit/vegetable utilization, and a selection among the suggestions was conducted by nutritionists and the school cooks. The selected meal was compared to a similar recipe from ChatGPT generated from a simple prompt with regard to their acceptance and emotions evoked. The two dishes were variations of carrot pie recipes including vegetable peel and were both prepared by experienced school cooks. A third recipe proposed by the school’s cooks was used as comparison. Parents’ perceptions towards whole food utilization to their children were elicited by sentence completion methodology. Results showed that children liked both their and the cooks’ recipes but rejected ChatGPT’s recipe. Both cooks’ and children’s carrot pies evoked positive emoji pairs, meanwhile ChatGPT’s carrot pie was associated to emojis of negative connotation. Texture and unfamiliar taste were cited to justify the rejection. For parents, the utilization of whole fruits/vegetable in children’s meals is perceived as a good and nutritious idea, but safety concerns were revealed. This work demonstrates co-design with school children and whole food utilization as actionable strategies towards reducing waste of nutritious resources. Moreover, the study reports an unsuccessful exploratory usage of ChatGPT through a task-focused prompt. This may suggest the importance of specifying the context of the task when prompting an AI, to compensate for contextual information that is implicitly available to humans. Concerns about safety aspects should be addressed to ensure parents’ support for whole vegetable utilization in school meals.
期刊介绍:
Food Quality and Preference is a journal devoted to sensory, consumer and behavioural research in food and non-food products. It publishes original research, critical reviews, and short communications in sensory and consumer science, and sensometrics. In addition, the journal publishes special invited issues on important timely topics and from relevant conferences. These are aimed at bridging the gap between research and application, bringing together authors and readers in consumer and market research, sensory science, sensometrics and sensory evaluation, nutrition and food choice, as well as food research, product development and sensory quality assurance. Submissions to Food Quality and Preference are limited to papers that include some form of human measurement; papers that are limited to physical/chemical measures or the routine application of sensory, consumer or econometric analysis will not be considered unless they specifically make a novel scientific contribution in line with the journal''s coverage as outlined below.