Towards diet management with automatic reasoning and persuasive natural language generation

Abstract

We devise a scenario where the interaction between man and food is mediated by an intelligent system that, on the basis of various factors, encourages or discourages the user to eat a specific dish. The main factors that the system need to account for are (1) the diet that the user intends to follow, (2) the food that s/he has eaten in the last days, and (3) the nutritional values of the dishes and their specific recipes. Automatic reasoning and Natural Language Generation (NLG) play a fundamental role in this project: the compatibility of a food with a diet is formalized as a Simple Temporal Problem (STP), while the NLG tries to motivate the user. In this paper we describe these two facilities and their interface.