Substituting for healthier foods, investigating food-choices transitions - Crossing disciplinary views on food substitutions acceptability – SHIFT

Excessive intake of sugars and salt are linked to deleterious consequences on Human health. Current strategies to design and favor healthier options have limited effects due to their poor acceptability. SHIFT proposes a multidisciplinary approach, combining life-, social- and computer-sciences to understand the determinants, mechanisms, and levers to modulate the acceptability of a meal option. This project will address precise alimentary situations where margins of improvement with respect to salt and sugar reduction are possible, ie. acceptability of (i) water or low energy beverages in substitution of sodas and (ii) sweet- or salt-reduced options at the end of main meals. Interdisciplinary research activities will be conducted at the populational, contextual and individual scales to decipher criteria driving the acceptability foods. The project will be based on 4 research activities (4 workpackages) conducted jointly on precise alimentary situations. A first workpackage will conduct Artificial Intelligence research to derive the criteria that drive the acceptability of a food proposition. Non-supervised machine learning of food substitutability and causality inference techniques will be implemented on massive sets of dietary records. A second workpackage will examine the role of the micro-sociological context on the choice of healthier meal propositions. Studies will primarily consist in observing and analyzing food behavior in a University restaurant setting to reveal the contextual dynamics through which a food proposition can evolve to be more acceptable by individuals. A third workpackage will combine behavioural neurosciences and computational neurosciences approaches to decipher the individual decision-making processes that underlie the acceptance or rejection of a food proposition. Functional Magnetic resonance imaging techniques will allow the exploration of brain circuits involved when a proposition becomes acceptable or not acceptable while theoretical tools of value-based decision-making will model the mechanisms by which social modulations affect food decisions. Finally, on the basis of all research conducted in WP1, 2 and 3, a fourth workpackage will develop and test in ecological consumptions situations, a food substitution recommender engine, allowing us to generate individual, nutritionally relevant and acceptable food swaps. The impact of such a recommender engine will be assessed in real life conditions and a specific attention will be paid to reductions in sugar and salt intakes. The results and lessons from SHIFT on the design of efficient, personalized and context-aware dietary recommender advices will ground innovative behavior change policies to reduce sugars and salt intakes for populations. SHIFT gathers 5 academic partners: The laboratory of “Physiologie de la Nutrition et du Comportement Alimentaire” (INRA-AgroParisTech, project leader), the “Institut des Systèmes Intelligents et de Robotique” (Sorbonne Université, CNRS-INSERM), the laboratory of “Mathématiques et Informatique Appliquées” (INRA-AgroParisTech), the laboratory of “Alimentation et Sciences Sociales” (INRA) and the School of Psychology of the University of Birmingham and an industrial partner: Danone Nutricia Research (Global Nutrition Department).