Optimal User-Interface for a virtual nutrition recommender system (FA5 module 3)

Individual tailored nutrition (TN) recommendations could contribute to the development of healthy nutritional habits. Food4Me, an EU-funded, randomized-controlled intervention study showed that nutritional recommendations based on individual nutritional habits can positively affect nutritional behavior (e.g. decrease in consumption of meat and salt) [1]. An effective realization of nutritional recommendations is biased by various factors. The likelihood of adopting healthy behaviors rises with the increase of individually perceived benefits and the decrease of individually perceived barriers (costs) [2].

Digital improvements as well as the increasing use of information- and communication techniques (ICT) in everyday life offer the chance to create electronic TN-recommender systems and make TN accessible for a multitude of users [3]. The acceptance of an electronic TN-recommender system can be improved by information on the effectiveness of the recommendation, a positive attitude of the user and the protection of personal data [4].

The impact of the communication between a user and a TN-recommender system on adopting nutritional recommendations has been studied sparsely within scientific research.

The obtained results will be applied to develop a prototype of a virtual nutritional recommender system, which will be tested within a virtual environment (e.g. supermarket). An optimized version of this prototype will be evaluated in a field study. Therefore, the prototype will be compared to virtual nutrition applications (APPetite and Nutrilize, enable1.0) as well as to an intervention with a personal human nutritionist. Changes in nutritional behavior of the participants and the user’s satisfaction will be examined.

Our objectives

The project aims to develop a user-interface for a virtual nutritional recommender system, which supports long-term positive changes within the nutritional behavior by maximizing the user’s benefit and minimizing the demand for the user.

  1. Identification of communication needs from a user’s point of view
  2. Analysis of cost and benefits of different user-interface characteristics
  3. Development and testing of a virtual nutritional recommender system prototype

We expect that adapting different electronic TN-systems to the user’s communication needs will improve the acceptance of such systems.

[1] Celis-Morales, Carlos, et al. "Effect of personalized nutrition on health-related behaviour change: evidence from the Food4me European randomized controlled trial." International journal of epidemiology 46.2 (2016): 578-588.
[2] Janz, Nancy K., and Marshall H. Becker. "The health belief model: A decade later." Health education quarterly 11.1 (1984): 1-47.
[3] Kraemer, K., et al. ".1 Personalized Nutrition: Paving the way to better population health." Good Nutrition: Perspectives for the 21st Century. Karger Publishers, 2016. 235-248.
[4] Poínhos, Rui, et al. "Psychological determinants of consumer acceptance of personalised nutrition in 9 European countries." PloS one 9.10 (2014): e110614.