Univerza na Primorskem Fakulteta za matematiko, naravoslovje in informacijske tehnologije
SI | EN

petek, 26. maj 2023 Arsen Matej GOLUBOVIKJ: Longitudinal Study of Preferences and Behaviour Changes in Music Streaming

V ponedeljek, 29. maja 2023, bo ob 16.00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 29. maj 2023 ob 16.00 v FAMNIT-VP2.

------------------------------------------------------
PREDAVATELJ: Arsen Matej GOLUBOVIKJ
------------------------------------------------------

Arsen Matej Golubovikj is a 1st year PhD student of Computer Science at UP FAMNIT. He finished his master's studies in Data Science at UP FAMNIT, and is now exploring topics related to Recommender Systems and User Modeling.

-----------------------------------------------------------------------------------------------------------------------
NASLOV: Longitudinal Study of Preferences and Behaviour Changes in Music Streaming
-----------------------------------------------------------------------------------------------------------------------

POVZETEK:

The majority of research in recommender systems, being it algorithmic improvements, context-awareness, explainability, or other areas, evaluate their systems on datasets that capture the user interaction with the system in a relatively limited time span. However, recommender systems have been around for more than two decades and the way user behave might have changed through time. Although there is a wide body of research in media studies and psychology on how user preferences and behaviour change through time (especially as users age) there has been very little work done in the domain of recommender systems. In this work we explore how user preferences and behaviour change through time on a well-known dataset of LastFM users, the LFM-2B dataset. To the best of our knowledge, this is the only dataset that covers a long-enough time span (to allow longitudinal studies) and has age information about its users. Beside performing a descriptive analysis of preferences and behaviour changes we also inspect whether there are differences between generations of users. The results show important insights that can pave the way for a new line of research in recommender systems and informs future work.

Seminar bo potekal v angleškem jeziku v predavalnici FAMNIT-VP2.

Vabljeni!