Interface-Aware Recommender Systems

Santiago de Leon Martinez

Kempelen Institute of Intelligent Technologies, Bratislava, Slovakia; Brno University of Technology, Brno, Czechia

Resumen/Abstract

Despite the wide-spread use of multi-list or carousel (Netflix-like) interfaces in e-commerce and streaming services, there is little academic research (less than 30 papers), especially when compared to works for single-list interfaces. Recent eye tracking results have shown that users browse multi-list and carousels significantly differently than other interfaces. Carousels are much more complex, allowing a wide-range of browsing/interaction sequences with multiple topic defined-lists that can be swiped to see more items. To account for this complexity and improve recommendations, recommender systems should be designed specifically for the interfaces they are used on, in other words Interface-Aware Recommender Systems.This is an adapted talk of the Interface-Aware Recommender Systems tutorial presented at UMAP 2026. It will introduce researchers and industry practitioners to the growing area of interface-aware recommenders. It provides an introduction to varying interface and their impact on user behavior, an overview of the research and insights for improving interface specific systems, the open problems and challenges that have not been addressed, and tools/datasets to help tackle these problems. The goal is to provide a strong basis and tools that participant can use to build improved user-centric systems that are interface-aware and also encourage future research in this area.

Curriculum ponente

Santiago de Leon Martinez is a Spanish-American PhD candidate in the MSCA Eyes4ICU Doctoral Network at the Kempelen Institute of Intelligent Technologies in Bratislava, Slovakia. His research focuses on interface-aware recommender systems, carousel-based recommendation interfaces, user modeling, and eye tracking. His work combines behavioral data, user modeling, and algorithmic development to better align recommender systems with real human behavior.He is the creator and first author of the RecGaze Dataset, the first publicly available dataset combining eye-tracking and interaction data for carousel-based recommender systems. His research spans both applied user modeling and algorithmic optimization, with a particular interest in representing users through behavioral data and incorporating those representations into intelligent systems.Prior to his doctoral studies, he earned a Master's degree in Health Information Engineering from the University Carlos III of Madrid and bachelor's degrees in Chemistry, Spanish Literature, and Theoretical Mathematics from the University of Kentucky. In 2018, he joined research groups in psychiatry at the Jiménez Díaz Foundation and machine learning at the University Carlos III of Madrid, where he began working at the intersection of medicine, behavioral science, user modeling, and artificial intelligence. He has also conducted research in mathematics, physics, and neurobiology.Santiago has authored more than 20 publications spanning mathematical number theory, psychiatry and psychology, machine learning, eye tracking, and recommender systems.