Intent-aware Music Recommender Systems
Intent-aware Music Recommender Systems
Disciplines
Computer Sciences (90%); Psychology (10%)
Keywords
-
Music Information Retrieval,
Music Recommender Systems,
Multimedia
The music that we prefer, such as a particular artist or genre, depends on our intended purpose for listening. For example, we may choose to listen to calming music after a long day at work but opt for upbeat music when preparing for a party. While music psychologists have identified several general intents for music listening, such as self-expression, mood regulation, and social connectedness, these intents are more nuanced. Unfortunately, current music recommender systems do not take user intents into account when making recommendations. Additionally, since music is a multifaceted and multimodal cultural commodity, the way a music item is represented (e.g., music video clip, digital score sheet, or audio file) limits its possible uses and the purpose it may serve for the listener. For instance, a music video clip may not be suitable for practicing piano, while a digital score sheet might be. Against this background, the project aims to research (1) novel algorithms that recognize a listener`s intent when accessing music-related content and (2) create a new generation of music recommender systems that recognize and adapt to user intents. Specifically, we will first identify and investigate the intents that drive users when accessing multimedia collections of music-related content. Then, we will create user preference models that integrate various content descriptors, including audio, textual, and visual characteristics of music items. Third, we will study which multimedia content descriptors are best suited to predict listening intents. In addition to analyzing content descriptors, we will explore the potential benefits of incorporating user and contextual aspects, such as demographics, personality traits, mood, activity, and social context, into the prediction model to improve its performance. Ultimately, we will integrate the user preference profiles and predicted intents to devise a new music recommendation algorithm that reacts dynamically to changing intents and explains its recommendations to the listener. The algorithm will be implemented in a prototype intent-ware music recommendation system.
- Universität Linz - 100%
- Eva Zangerle, Universität Innsbruck , national collaboration partner
- Michael Huber, Universität für Musik und darstellende Kunst Wien , national collaboration partner
- Francesco Ricci, Libera Università di Bolzano - Italy
- Cremonesi Paolo, Polytechnic University of Milan - Italy
- Alan Hanjalic, Delft University of Technology - Netherlands
- Martijn Willemsen, Technische Universiteit Eindhoven - Netherlands
- Xavier Serra, Universitat Pompeu Fabra - Spain
Research Output
- 38 Citations
- 11 Publications
-
2023
Title Emotion-aware music tower blocks (EmoMTB ): an intelligent audiovisual interface for music discovery and recommendation DOI 10.1007/s13735-023-00275-8 Type Journal Article Author Melchiorre A Journal International Journal of Multimedia Information Retrieval Pages 13 Link Publication -
2024
Title Simultaneous Unlearning of Multiple Protected User Attributes From Variational Autoencoder Recommenders Using Adversarial Training DOI 10.1007/978-3-031-71975-2_7 Type Book Chapter Author Escobedo G Publisher Springer Nature Pages 91-102 -
2024
Title Modular Debiasing of Latent User Representations in Prototype-Based Recommender Systems DOI 10.1007/978-3-031-70341-6_4 Type Book Chapter Author Melchiorre A Publisher Springer Nature Pages 56-72 -
2024
Title Making Alice Appear Like Bob: A Probabilistic Preference Obfuscation Method For Implicit Feedback Recommendation Models DOI 10.1007/978-3-031-70368-3_21 Type Book Chapter Author Escobedo G Publisher Springer Nature Pages 349-365 -
2024
Title A Multimodal Single-Branch Embedding Network for Recommendation in Cold-Start and Missing Modality Scenarios DOI 10.1145/3640457.3688138 Type Conference Proceeding Abstract Author Ganhör C Pages 380-390 Link Publication -
2024
Title Oh, Behave! Country Representation Dynamics Created by Feedback Loops in Music Recommender Systems DOI 10.1145/3640457.3688187 Type Conference Proceeding Abstract Author Lesota O Pages 1022-1027 Link Publication -
2024
Title The Impact of Differential Privacy on Recommendation Accuracy and Popularity Bias DOI 10.1007/978-3-031-56066-8_33 Type Book Chapter Author Müllner P Publisher Springer Nature Pages 466-482 -
2024
Title Measuring Bias in Search Results Through Retrieval List Comparison DOI 10.1007/978-3-031-56069-9_2 Type Book Chapter Author Ratz L Publisher Springer Nature Pages 20-34 -
2024
Title Content-driven music recommendation: Evolution, state of the art, and challenges DOI 10.1016/j.cosrev.2024.100618 Type Journal Article Author Deldjoo Y Journal Computer Science Review Pages 100618 Link Publication -
2023
Title Exploring emotions in Bach chorales: a multi-modal perceptual and data-driven study DOI 10.1098/rsos.230574 Type Journal Article Author Parada-Cabaleiro E Journal Royal Society Open Science Pages 230574 Link Publication -
2024
Title Psychology-informed Information Access Systems Workshop DOI 10.1145/3616855.3635722 Type Conference Proceeding Abstract Author Schedl M Pages 1216-1217