Predicting individual food valuation via vision-language embedding model
PLOS Digital Health · 28.10.2025 · 4 (10) · e0001044
DOI: 10.1371/journal.pdig.0001044 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS Digital Health, online erschienen am 28.10.2025. Verfasst von Hiroki Kojima und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information Medicine, National Institute of Neuroscience, National Center of Neurology and Psychiatry, Kodaira, Tokyo, Japan. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Society for the Promotion of Science, Japan Science and Technology Agency, National Center of Neurology and Psychiatry.
Abstract (Originalsprache)
Food preferences differ among individuals, and these variations reflect underlying personalities or mental tendencies. However, capturing and predicting these individual differences remains challenging. Here, we propose a novel method to predict individual food preferences by using CLIP (Contrastive Language-Image Pre-Training), which can capture both visual and semantic features of food images. By applying this method to food image rating data obtained from human subjects, we demonstrated our method’s prediction capability, which achieved better scores compared to methods using pixel-based embeddings or label text-based embeddings. Our method can also be used to characterize individual traits as characteristic vectors in the embedding space. By analyzing these individual trait vectors, we captured the tendency of the trait vectors of the high picky-eater group. In contrast, the group with relatively high levels of general psychopathology did not show any bias in the distribution of trait vectors, but their preferences were significantly less well-represented by a single trait vector for each individual. Our results demonstrate that CLIP embeddings, which integrate both visual and semantic features, not only effectively predict food image preferences but also provide valuable representations of individual trait characteristics, suggesting potential applications for understanding and addressing food preference patterns in both research and clinical contexts.
Autor:innen und Institutionen
- Department of Information Medicine, National Institute of Neuroscience, National Center of Neurology and Psychiatry, Kodaira, Tokyo, Japan.
- Hitotsubashi Institute for Advanced Study, Hitotsubashi University, Kunitachi, Tokyo, Japan.
- Graduate School of the Humanities, Senshu University, Kawasaki, Kanagawa, Japan.
- Faculty of Social Data Science, Hitotsubashi University, Kunitachi, Tokyo, Japan.
- Centre for Brain, Mind and Markets, The University of Melbourne, Melbourne, Australia.
ORCID-Profile: Hiroki Kojima, Yuichi Yamashita
Förderung
- Japan Society for the Promotion of Science
- Japan Science and Technology Agency
- National Center of Neurology and Psychiatry
Zitieren
APA
Kojima, H., Toyama, A., Suzuki, S., & Yamashita, Y. (2025). Predicting individual food valuation via vision-language embedding model. PLOS Digital Health, 4(10), e0001044. https://doi.org/10.1371/journal.pdig.0001044
Vancouver
Kojima H, Toyama A, Suzuki S, Yamashita Y. Predicting individual food valuation via vision-language embedding model. PLOS Digital Health. 2025;4(10):e0001044. doi:10.1371/journal.pdig.0001044
BibTeX
@article{Kojima2025,
author = {Kojima, Hiroki and Toyama, Asako and Suzuki, Shinsuke and Yamashita, Yuichi},
title = {Predicting individual food valuation via vision-language embedding model},
journal = {PLOS Digital Health},
year = {2025},
volume = {4},
number = {10},
pages = {e0001044},
doi = {10.1371/journal.pdig.0001044}
}
EUVIMED