MeshUp #23 - Beyond Engagement: Rethinking Music Recommendation for Affect Regulation and Well-Being
This week, Vinoo Alluri will present Beyond Engagement: Rethinking Music Recommendation for Affect Regulation and Well-Being.
Abstract
Music streaming platforms rely on listeners’ digital footprints to personalize the listening experience, often optimizing for engagement. However, this risks conflating what people want, as inferred from observable music consumption, with what they may actually need. As a result, recommendation algorithms may become increasingly effective at predicting and optimizing behavior while remaining poorly aligned with individuals’ underlying values and needs, potentially leading to suboptimal recommendations and unintended harms. In my talk, I will summarize our efforts to model online music consumption across platforms such as Last.fm and Spotify and its associations with individual traits. I will present preliminary findings on the interactions between individual traits, emotion regulation strategies, and well-being, and cultural differences thereof. I will also describe our initial foray into modelling dynamic affective trajectories in relation to online music listening, with the aim of understanding music consumption in the context of affect regulation. Finally, I will discuss how associations between individual traits and model parameters could inform the development of intervention-oriented recommendation systems that move beyond predicting engagement and instead seek to steer recommendations toward supporting listeners’ well-being and regulatory needs.
Bio
Dr. Vinoo Alluri is an Associate Professor at the Cognitive Science Lab at the International Institute of Information Technology-Hyderabad, India. She has a background in Electronics and Communication Engineering, after which she pursued a Masters in Music Engineering Technology at the University of Miami, and a Ph.D. in Musicology from the University of Jyväskylä, Finland. Her work is highly interdisciplinary involving music psychology, music information retrieval, and neuroscience. Currently she is working on projects that examine music listening habits on online streaming platforms and social media in relation to individual differences and mental health. Other ongoing projects focus on the interpretability of artificial auditory neural networks and the generation of music to enhance narrative experiences of books. More information can be found here: https://mcgiiit.com/about
Access
MishMash MeetUps are short, informal meetings in the consortium where both early career and established researchers present ongoing projects. The events are open for everyone, but, for security reasons, Zoom links are only provided to people that are affiliated with a MishMash Work Package. If not, please ask for access.
Subscribe to all events (webcal)
Download calendar (ICS)
If the webcal link doesn't open in your calendar (e.g. Outlook), use "Download calendar (ICS)" and open the file in your calendar app.