Investigating Health-Aware Smart-Nudging with Machine Learning to Help People Pursue Healthier Eating-Habits

Abstract

Food-choices and eating-habits directly contribute to our long-term health. This makes the food recommender system a potential tool to address the global crisis of obesity and malnutrition. Over the past decade, artificial-intelligence and medical researchers became more invested in researching tools that can guide and help people make healthy and thoughtful decisions around food and diet. In many typical (Recommender System) RS domains, smart nudges have been proven effective in shaping users' consumption patterns. In recent years, knowledgeable nudging and incentifying choices started getting attention in the food domain as well. To develop smart nudging for promoting healthier food choices, we combined Machine Learning and RS technology with food-healthiness guidelines from recognized health organizations, such as the World Health Organization, Food Standards Agency, and the National Health Service United Kingdom. In this paper, we discuss our research on, persuasive visualization for making users aware of the healthiness of the recommended recipes. Here, we propose three novel nudging technology, the WHO-BubbleSlider, the FSA-ColorCoading, and the DRCI-MLCP, that encourage users to choose healthier recipes. We also propose a Topic Modeling based portion-size recommendation algorithm. To evaluate our proposed smart-nudges, we conducted an online user study with 96 participants and 92250 recipes. Results showed that, during the food decision-making process, appropriate healthiness cues make users more likely to click, browse, and choose healthier recipes over less healthy ones.

Ethical and legal considerations for nutrition virtual coaches

“…Uniformity of infographic such as dietary pyramid and plate [186,196,197] Informative and assistive systems PI3.1 Higher food cost of recommended healthy dietary patterns Granting comprehensive information to ensuring comparison between food and substitution [163] PI3.2 User with cognitive disorders or mental issues IAT functionalities to be determined according patients' needs [198] Persuasive systems PI4.1 Nudging healthy and environmental nutritional choices is a persuasion technique Careful evaluation of consumers' behavior when setting choice architecture to nudge behavior [199,200] PI4.2 Ensure transparency on NVC goals Setting clear goal statement on seeked health and environmental impact outcomes boundaries, providing transparency, stating the goals clearly, and preventing unintended behavior change. Moreover, we have related ethical challenges to the NVC sphere, elaborating on the food sustainability from both virtual assistant and user perspectives.…”

“…PI4.1 Nudging in persuasive technologies (linked to EC4.1 and LC4.2): Smart-nudging techniques have also been proven effective in information technologies to nudge healthy nutritional choices [199]. A nudging intervention is a change in the choice architecture environment to gently push behavior.…”