Nudging Healthy Choices in Food Search Through Visual Attractiveness

Abstract

Recipe websites are becoming increasingly popular to support people in their home cooking. However, most of these websites prioritize popular recipes, which tend to be unhealthy. Drawing upon research on visual biases and nudges, this paper investigates whether healthy food choices can be supported in food search by depicting attractive images alongside recipes, as well as by re-ranking search results on health. After modelling the visual attractiveness of recipe images, we asked 239 users to search for specific online recipes and to select those they liked the most. Our analyses revealed that users tended to choose a healthier recipe if a visually attractive image was depicted alongside it, as well as if it was listed at the top of a list of search results. Even though less popular recipes were promoted this way, it did not come at the cost of a user’s level of satisfaction.

PROTEIN AI Advisor: A Knowledge-Based Recommendation Framework Using Expert-Validated Meals for Healthy Diets

“…The evaluation of the proposed approach was performed by employing 17 users that selected a single meal from a choice of 4 meals. In another work [ 39 ], the same authors studied how the inclusion of food images (i.e., visual attractiveness) alongside meals can shift users towards healthier meal options, evaluating their approach by employing 239 users who stated their preferred meal out of a set of options. Finally, in [ 40 ], the authors proposed a food recommendation system that takes into consideration users’ ratings of ingredients to predict preferred meals in a set of meal options.…”

Situated Affectivity and Mind Shaping: Lessons from Social Psychology

“…Once situationist research has revealed the way in which agents are influenced by the presence or absence of certain odours, tastes, objects, people etc., those variables can be deliberately manipulated in order to nudge people towards beneficial behaviour without forcing, incentivizing or trying to rationally convince them to do so. 14 Mind shaping of this kind has already proven to be effective, for instance, in connection with healthy eating habits (Vecchio & Cavallo, 2019), where the positioning of healthy food options on menus (Keegan et al, 2019) or healthy food recipes on food platforms (Starke et al, 2021) affects people’s dietary choices. It can also encourage more sustainable consumption habits (e.g., Demarque et al, 2015; Lehner et al, 2016) by increasing people’s willingness to use reusable takeaway boxes (Dorn & Stoeckli, 2018) or cups (Loschelder et al, 2019) or reducing meat consumption (May & Kumar, 2022; Sparkman et al, 2020) and ideological biases on climate change (Goldberg et al, 2020; Sparkman et al, 2021).…”

Developing and Evaluating a University Recommender System

“…In domains where the "decision stakes" are higher, because the user decision is important or costly, the recommender approaches or algorithms should also be aimed at optimizing diversity and longerterm preferences, instead of maximizing short-term engagement only. This applies to, for instance, recommender systems that promote healthy foods or suggestions for real estate (Yuan et al, 2013;Starke and Trattner, 2021;Starke et al, 2021b).…”