ponedeljek, 11. maj 2026 Arsen Matej GOLUBOVIKJ: Rethinking Subjective Features in Recommender Systems: Personal Views Over Aggregated Values & Nadun Liyanage: Passenger Experience in Autonomous Vehicles
V ponedeljek, 11. maja 2026, bodo ob 16:00 uri izvedeni dve
predavanji v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.
ČAS/PROSTOR: 11. maj 2026 ob 16.00 v FAMNIT-VP3.
1. predavanje:
============
-------------------------------------------------------
PREDAVATELJ: Arsen Matej GOLUBOVIKJ
-------------------------------------------------------
Arsen Matej Golubovikj is currently a teaching assistant and a PhD student in the HICUP Lab at UP FAMNIT, under the supervision of prof. Marko Tkalčič. His academic interests encompass recommender systems, and user modeling, primarily in subjective domains, such as music recommendation and movie recommendation. His doctoral work explores user-centric recommender systems that account for subjective item perspectives.
--------------------------------------------------------------------------------------------------------------------------------------------------
NASLOV: Rethinking Subjective Features in Recommender Systems: Personal Views Over Aggregated Values
--------------------------------------------------------------------------------------------------------------------------------------------------
POVZETEK:
Subjective features of content items, such as emotional resonance and aesthetic quality, have become increasingly important in recommender systems (RecSys), as the field moves beyond objective content and behavioral signals. Traditionally, such features were treated as fixed item-level properties, aggregated across users. However, emerging evidence suggests that subjective features are inherently user-dependent, shaped by individual interpretations and personal perspectives. This paper presents the first direct comparison between fixed (aggregated) and user-specific (subjective) item representations for modeling subjective features in RecSys. Using three datasets spanning movies, videos, and images, with subjective features, such as eudaimonia, hedonia, emotion, and aesthetics, we evaluate the impact of the representation strategy (i.e. fixed vs. user-specific) on recommendation performance across multiple algorithms. Our findings show that user-specific representations consistently outperform aggregate ones, often with statistically significant improvements. These results underscore the importance of modeling subjectivity at the user level, offering concrete guidance for more personalized and effective recommendation systems.
Seminar bo potekal v angleškem jeziku.
=============================================================================================================
2. predavanje:
============
--------------------------------------------
PREDAVATELJ: Nadun LIYANAGE
--------------------------------------------
Nadun Liyanage is a doctoral researcher at University of Primorska - HICUP Lab. His work explores how immersive technologies can improve interactions in vehicles and transportation contexts, such as driver assistance, infotainment, and user experience in future mobility systems.
----------------------------------------------------------------------------
NASLOV: Passenger Experience in Autonomous Vehicles
----------------------------------------------------------------------------
POVZETEK:
Autonomous vehicles (AVs) shift mobility from a driver-centered task to a passenger-centered experience, making comfort, trust, and overall passenger experience critical determinants of acceptance. This review synthesizes empirical research on passenger experience in AV contexts, with particular attention to immersive interventions (e.g., AR/VR) and the realism of experimental methodologies used to study AV travel. We analyze 32 peer-reviewed studies and organize them into a structured design space spanning (i) experimental platform and in-vehicle setup (simulator vs. real-world driving, driving mode, cabin representation, motion cueing, and display technologies), (ii) study focus and in-scenario roles (passenger/driver/pedestrian, scenarios, and controlled sensory focus), and (iii) measurement strategy and domains (comfort factors, subjective and objective measures, and focus conditions). Alluvial diagrams and complementary quantitative visualizations reveal strong coupling between methodological choices: simulator studies frequently depend on displays and often lack high-fidelity motion cueing, whereas real-world studies naturally provide full motion cues but more often avoid additional displays. Across the literature, visual interventions dominate, while multisensory approaches (auditory, haptic, olfactory) and standardized, multimodal measurement triangulation are less common. Based on these trends, we outline research opportunities for future AV passenger-experience studies, including higher-fidelity experimental setups that combine motion cueing with immersive displays, better separation of “perceived autonomy” confounds such as driver presence/visibility, and more systematic evaluation frameworks that integrate subjective experience with physiological, behavioral, and vehicle/system measures.
Seminar bo potekal v angleškem jeziku.
=============================================================================================================
Seminarja bosta potekala v predavalnici FAMNIT-VP3 s pričetkom ob 16:00 uri.
Vabljeni!
