Comparison of Answers between ChatGPT and Human Dieticians to Common Nutrition Questions
Journal of Nutrition and Metabolism · 07.11.2023 · 2023 · 1-9
DOI: 10.1155/2023/5548684 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Nutrition and Metabolism, erschienen am 07.11.2023. Verfasst von Daniel Kirk und 2 weiteren Autor:innen. Beteiligte Einrichtung: Division of Human Nutrition and Health, Wageningen University & Research, Helix, Stippeneng 4, Wageningen 6708 WE, Netherlands. Die Arbeit wurde bisher 64-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
More people than ever seek nutrition information from online sources. The chatbot ChatGPT has seen staggering popularity since its inception and may become a resource for information in nutrition. However, the adequacy of ChatGPT to answer questions in the field of nutrition has not been investigated. Thus, the aim of this research was to investigate the competency of ChatGPT in answering common nutrition questions.
Methods
Dieticians were asked to provide their most commonly asked nutrition questions and their own answers to them. We then asked the same questions to ChatGPT and sent both sets of answers to other dieticians (N = 18) or nutritionists and experts in the domain of each question (N = 9) to be graded based on scientific correctness, actionability, and comprehensibility. The grades were also averaged to give an overall score, and group means of the answers to each question were compared using permutation tests.
Results
The overall grades for ChatGPT were higher than those from the dieticians for the overall scores in five of the eight questions we received. ChatGPT also had higher grades on five occasions for scientific correctness, four for actionability, and five for comprehensibility. In contrast, none of the answers from the dieticians had a higher average score than ChatGPT for any of the questions, both overall and for each of the grading components.
Conclusions
Our results suggest that ChatGPT can be used to answer nutrition questions that are frequently asked to dieticians and provide encouraging support for the role of chatbots in offering nutrition support.
Autor:innen und Institutionen
- Division of Human Nutrition and Health, Wageningen University & Research, Helix, Stippeneng 4, Wageningen 6708 WE, Netherlands.
- Department of Twin Research and Genetic Epidemiology, King's College London, St Thomas' Hospital Campus, 4th Floor South Wing Block D, Westminster Bridge Rd, London SE1 7EH, UK.
- OnePlanet Research Center, Plus Ultra II, Bronland 10, Wageningen 6708 WE, Netherlands.
ORCID-Profile: Daniel Kirk, Elise van Eijnatten, Guido Camps
Zitieren
APA
Kirk, D., van Eijnatten, E., & Camps, G. (2023). Comparison of Answers between ChatGPT and Human Dieticians to Common Nutrition Questions. Journal of Nutrition and Metabolism, 2023, 1-9. https://doi.org/10.1155/2023/5548684
Vancouver
Kirk D, van Eijnatten E, Camps G. Comparison of Answers between ChatGPT and Human Dieticians to Common Nutrition Questions. Journal of Nutrition and Metabolism. 2023;2023:1-9. doi:10.1155/2023/5548684
BibTeX
@article{Kirk2023,
author = {Kirk, Daniel and van Eijnatten, Elise and Camps, Guido},
title = {Comparison of Answers between ChatGPT and Human Dieticians to Common Nutrition Questions},
journal = {Journal of Nutrition and Metabolism},
year = {2023},
volume = {2023},
pages = {1--9},
doi = {10.1155/2023/5548684}
}
EUVIMED