Can children and artificial intelligence be sources of ideas for school meal preparations based on whole food utilization?

•Carrot peel pies created by children, school’s cooks and ChatGPT were evaluated.•Meals created by children and cooks had good acceptance and evoked positive emotions.•Sample proposed by ChatGPT were rejected and evoked negative emotions.•Parents believe whole food utilization is good idea and nutri...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Food quality and preference 2025-02, Vol.123, p.105349, Article 105349
Hauptverfasser: Goulart, Fabrício, Sant’Anna, Voltaire, Almli, Valérie L., Tolotti Maschio, Gabriel
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:•Carrot peel pies created by children, school’s cooks and ChatGPT were evaluated.•Meals created by children and cooks had good acceptance and evoked positive emotions.•Sample proposed by ChatGPT were rejected and evoked negative emotions.•Parents believe whole food utilization is good idea and nutritious.•For parents, such meals need to be taste and safe for consumption. 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 implici
ISSN:0950-3293
DOI:10.1016/j.foodqual.2024.105349