Title

Algorithmic Auditing for Music Discoverability: Engaging Users to Broaden Cultural Diversity in Recommender Systems

Abstract

In this talk I will present AA4MD (Algorithmic Auditing for Music Discoverability), a Marie Skłodowska-Curie Actions initiative aiming to explore and mitigate problematic behaviors in music recommendation systems that limit exposure to culturally diverse content. Indeed, as streaming platforms and algorithmic recommenders increasingly mediate how audiences discover music, concerns have emerged around fairness, inclusion, non-discrimination, and transparency. A4MD adopts a human-centred auditing approach: combining qualitative and quantitative methods to understand user experiences; developing a web-based tool for large-scale audits of real recommender systems; and deriving policy recommendations to support more inclusive music discoverability. By involving end users directly in the auditing process, the project seeks not only to identify bias or hidden filters in existing systems but also to pave the way for system designs and policies that amplify under-represented music.

Bio

Lorenzo Porcaro is a research scientist specialising in recommender systems with a particular focus on algorithmic auditing. He is currently a Marie Skłodowska-Curie Postdoctoral Fellow at Sapienza University of Rome, leading the project Algorithmic Auditing for Music Discoverability (AA4MD). Lorenzo holds a PhD from Universitat Pompeu Fabra, where his doctoral work investigated how diversity in music recommendations affects listener behaviour and perception. Before his PhD, Lorenzo gained industry experience in music data engineering at Soundcloud and BMAT, and he later worked as Scientific Project Officer at the European Commission’s Joint Research Centre, contributing to the European Centre for Algorithmic Transparency.

Website: https://aa4md-project.eu/

Video: https://youtu.be/uq3q-PCFvqc

Activity in the frame of:

Cátedra UPF-BMAT en Inteligencia Artificial y Música (TSI-100929-2023-1). Project funded by Secretaría de Estado de Digitalización e Inteligencia Artificial, the European Union-Next Generation EU, and by BMAT Music Innovators, the Music Operating System