1. médialab Sciences Po
  2. News
  3. Modeling User Preferences for Music Recommendations with LLMs: Opportunities and Limitations

Modeling User Preferences for Music Recommendations with LLMs: Opportunities and Limitations

The médialab seminar welcomes Elena Epure and Bruno Sguerra for a presentation on the use of NLP methods in music recommendation algorithms.

Event, Research Seminar

⇥

salle Goguel, 56 rue des saint pères, 75007 Paris

Abstract

"This talk explores the potential of large language models (LLMs) in enhancing music recommendation systems through explicit modeling of user preferences. We begin by comparing traditional recommenders with the capabilities introduced by LLMs. The discussion will focus on strategies for capturing preferences within conversations and extending to long-term user modeling beyond conversations. While we will examine the effectiveness of LLMs in various tasks, such as query parsing and user preference summarization, we will also address their limitations. The goal is to provide a comprehensive view of the challenges involved in modeling user preferences from and through text in the music domain."

Biography

Elena Epure is a Senior NLP Research Scientist at Deezer Research. She has a multidisciplinary educational background in computer science, digital humanities, and business, complemented by diverse professional experience in research, software engineering, consultancy, and teaching. Elena's current research focuses on creative media, building on her previous work with social media and news content. Her work integrates NLP fundamentals, including semantics, text mining, and information extraction, to advance creative media understanding, personalization, and contextualization. She also explores topics relayed to conversational and natural language recommendation and search.

Bruno Sguerra is a research scientist at Deezer Research. His work encompasses various aspects of user behavior, including investigations into search intent, modeling listening contexts, and improving music recommendation. His current interests focus on using interaction logs to explore and expand on traditional psychological paradigms. Recently, he has concentrated on studying the mere exposure effect and how repeated exposure shapes users' perception of music, with potential applications for understanding music preferences and discovery.

Practical information

The session will take place on Tuesday, February 18, 2025, from 2:00 PM to 4:00 PM, in person and in english at Sciences Po, Room Goguel, 56 rue des Saints-Pères, Paris 75007.


Prior registration is mandatory.