4TU.Redesign members Donika Xhani from the University of Twente, together with Kathleen Guan from TU Delft and other collaborators, have published a new paper titled “Modelling Food and Mood Relation with Dynamic Personas: An Ontology-Driven RAG-Based Recommendation Approach”.

In this work, the authors propose an ontology-driven recommendation approach that models the relationship between food and mood through the use of dynamic personas and Retrieval-Augmented Generation (RAG). The research combines semantic technologies, personalized recommendation systems, and explainable AI to support adaptive food recommendations tailored to users’ emotional states, preferences, and contextual factors.

The paper was co-authored by Donika Xhani, Kathleen Guan, Ausrine Ratkute, Caroline Figueroa, Renata Guizzardi, Jos van Hillegersberg, and Gayane Sedrakyan, representing a collaboration between researchers from the University of Twente and TU Delft.

Reference: Xhani D, Guan K, Ratkute A, Figueroa C, Guizzardi R, van Hillegersberg J, Sedrakyan G. Modelling Food and Mood Relation with Dynamic Personas: An Ontology-Driven RAG-Based Recommendation Approach.