Abstract
Effective recommendations on healthy food choice need to be personalized and sent out on a large scale. In this paper, we present a model of automatic message selection tailored on the characteristics of the recipient and focused on the reduction of red meat consumption. This model is obtained through the collaboration between social psychologists and artificial intelligence experts. Starting from selected psychosocial models on food choices and the framing effects of recommendation messages, we involved a sample of Italian participants in an experiment in which they: (a) filled out a first questionnaire, which was aimed at detecting the psychosocial antecedents of the intention to eat red/processed meat; (b) read messages differing as to the framing of the hypothetical consequences of reducing (gain, non-loss) versus not reducing (non-gain, loss) red/processed meat consumption; (c) filled out a second questionnaire, which was aimed at detecting participants’ reaction to the messages, as well as any changes in their intention to consume red/processed meat. Data collected were then employed to learn both the structure and the parameters of a Graphical Causal Model (GCM) based on a Dynamic Bayesian Network (DBN), aimed to predicting the potential effects of message delivery from the observation of the psychosocial antecedents. Such probabilistic predictor is intended as the basis for developing automated interactions strategies using Deep Reinforcement Learning (DRL) techniques. Discussion focuses on how to develop automatic interaction strategies able to foster mindful eating, thanks to (a) considering the psychosocial characteristics of the people involved; (b) sending messages tailored on these characteristics; (c) adapting interaction strategies according to people’s reactions.
Highlights
Red/Processed Meat Consumption has substantial effects on people’s health, such as an increased likelihood of developing various cancer and type 2 diabetes (Misra et al, 2018; Bianchi et al, 2019)
The procedure adopted was an automated search among all the possible Dynamic Bayesian Network (DBN) structures obeying to specific constraints allowing the causal interpretation that will be described
Thanks to the integration of theoretical models developed in the field of social psychology and the possibilities of probabilistic calculation allowed by Artificial Intelligence (AI), in this study we have developed a procedure to personalize messages aimed at favoring the reduction of RPMC, and thereby make them more effective
Summary
Red/Processed Meat Consumption ( on RPMC) has substantial effects on people’s health, such as an increased likelihood of developing various cancer and type 2 diabetes (Misra et al, 2018; Bianchi et al, 2019) For this reason, health authorities (e.g., World Health Organization, 2015) have recommended eating no more than 3 ounces (85 g) per meal, no more than a couple of times a week. Despite multiple government and social initiatives aimed at promoting meat reduction, people still face many difficulties in following recommendations in this direction (Stoll-Kleemann and Schmidt, 2017) Is it possible to think of a communication on healthy eating that is effective, personalized and at the same time addressed to many people? AI can, starting from psychosocial models, assess their predictive capacity, as well as simulate their application to larger populations
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
