Investigating the Impact of Audio States & Transitions for Track Sequencing in Music Streaming Sessions

Abstract

Music streaming is inherently sequential in nature, with track sequence information playing a key role in user satisfaction with recommended music. In this work, we investigate the role audio characteristics of music content play in understanding music streaming sessions. Focusing on 18 audio attributes (e.g. dancability, acousticness, energy), we formulate audio transitioning in a session as a multiple changepoint detection problem, and extract latent states of different audio attributes within each session. Based on insights from large scale music streaming data from a popular music streaming platform, we investigate questions around the extent to which audio characteristics fluctuate within streaming sessions, the heterogeneity across different audio attributes and their impact on user satisfaction. Furthermore, we demonstrate the promise of such audio-based characterizing of sessions in better sequencing tracks in a session, and highlight the potential gains in user satisfaction on offer. We discuss implications on the design of track sequencing models, and identify important prediction tasks to further research on the topic.

Related

August 2021 | KDD

Neural Instant Search for Music and Podcast

Helia Hashemi, Aasish Pappu, Mi Tian, Praveen Ravichandran, Mounia Lalmas, Ben Carterette

July 2021 | SIGIR

Podcast Metadata and Content: Episode Relevance and Attractiveness in Ad Hoc Search

Ben Carterette, Rosie Jones, Gareth Jones, Maria Eskevich, Sravana Reddy, Ann Clifton, Yongze Yu, Jussi Karlgren and Ian Soboroff

July 2021 | SIGIR

Current Challenges and Future Directions in Podcast Information Access

Rosie Jones, Hamed Zamani, Markus Schedl, Ching-Wei Chen, Sravana Reddy, Ann Clifton, Jussi Karlgren, Helia Hashemi, Aasish Pappu, Zahra Nazari, LongQi Yang, Oguz Semerci, Hugues Bouchard, Ben Carterette