An Approach for Social-Distance Preserving Location-Aware Recommender Systems: A Use Case in a Hospital Environment

Currently, the volume of geo-referenced data is rapidly expanding, and users frequently show interest in nearby items. Consequently, Location-Aware Recommender Systems (LARS) have garnered considerable attention from the research community in recent years. However, these systems are not ideally suited for situations where social distancing is crucial for people's safety, such as during the COVID-19 pandemic. In this paper, we study this problem through a use case scenario: recommending items for observation during an open-door hospital visit. We propose an approach for Side-LARS (SocIal-Distance prEserving LARS), a trajectory and user-based collaborative filtering algorithm, that incorporates location data, user behaviors and social distancing constraints to provide personalized recommendations. The experimental results demonstrate the effectiveness of the proposal in maintaining social distancing while providing personalized recommendations.