Towards a Spatio-Temporal Agent-Based Recommender System.

Agent-based recommender systems have been widely employed in the last years to provide informative suggestions to users, showing the advantage of exploiting components like beliefs, goals, and trust in the recommendation computation. However, many real-world recommendation scenarios, like the traffic or the health ones, require to represent and reason about spatial and temporal knowledge, considering also their inner incomplete and vague connotation. This paper tackles this challenge and introduces STARS, an agent-based recommender system based on the Belief-Desire-Intention (BDI) architecture. Our approach extends the BDI model with spatial and temporal reasoning to represent and reason about fuzzy beliefs and desires dynamics.