Beyond Class Stratification: The Rise of the Eclectic Music Consumer in the Modern Age

Nuccio, Massimiliano; Guerzoni, Marco; Katz‐Gerro, Tally

doi:10.1177/1749975518786039

Cited by 6 publications

(7 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead, he attributes it to the diversity of the stated preferences of people of the upper class, whereas the preferences of members of lower-status classes appear more exclusive. Later work, studying music taste in the “modern age” ( Nuccio et al, 2018 ), found little evidence that musical taste is indeed aligned with class position.…”

Section: Conceptual Background and Related Workmentioning

confidence: 99%

Listener Modeling and Context-Aware Music Recommendation Based on Country Archetypes

Schedl

Bauer

Reisinger

et al. 2021

Front. Artif. Intell.

View full text Add to dashboard Cite

Music preferences are strongly shaped by the cultural and socio-economic background of the listener, which is reflected, to a considerable extent, in country-specific music listening profiles. Previous work has already identified several country-specific differences in the popularity distribution of music artists listened to. In particular, what constitutes the “music mainstream” strongly varies between countries. To complement and extend these results, the article at hand delivers the following major contributions: First, using state-of-the-art unsupervized learning techniques, we identify and thoroughly investigate (1) country profiles of music preferences on the fine-grained level of music tracks (in contrast to earlier work that relied on music preferences on the artist level) and (2) country archetypes that subsume countries sharing similar patterns of listening preferences. Second, we formulate four user models that leverage the user’s country information on music preferences. Among others, we propose a user modeling approach to describe a music listener as a vector of similarities over the identified country clusters or archetypes. Third, we propose a context-aware music recommendation system that leverages implicit user feedback, where context is defined via the four user models. More precisely, it is a multi-layer generative model based on a variational autoencoder, in which contextual features can influence recommendations through a gating mechanism. Fourth, we thoroughly evaluate the proposed recommendation system and user models on a real-world corpus of more than one billion listening records of users around the world (out of which we use 369 million in our experiments) and show its merits vis-à-vis state-of-the-art algorithms that do not exploit this type of context information.

show abstract

Section: Conceptual Background and Related Workmentioning

confidence: 99%

Listener Modeling and Context-Aware Music Recommendation Based on Country Archetypes

Schedl

Bauer

Reisinger

et al. 2021

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…de Boise, 2016; Prieur & Savage, 2013; Rimmer, 2012), versions of this argument continue to be made (e.g. Ferrant, 2018; Nuccio, Guerzoni, & Katz-Gerro, 2018), which, in reproducing the figure of the omnivore, ultimately suggest a severance between class and taste.…”

Section: Social Class Taste and Boxingmentioning

confidence: 98%

On white-collar boxing and social class

Wright

2019

The Sociological Review

View full text Add to dashboard Cite

This article is based on the first sociological research of white-collar boxing in the UK. Grounded in an ethnography of a boxing gym in the Midlands, the article argues that the term ‘white-collar boxing’ in this context is immediately misleading, and entails the term being used in a way with which sociologists are unaccustomed. Whereas white-collar boxing originated in the context of post-industrial New York City as a pastime only for the extremely wealthy, the situation in the UK is different. Participants actively reject this understanding of white-collar boxing. The term white-collar boxing does not signify the social class of participants, but refers to their novice status. Given that boxing is an example through which Bourdieu’s theory of distinction is discussed, and that white-collar boxing is a distinctly late-modern version of the sport containing an erroneous class signifier, this version of the sport is a site through which such discussions of consumption can be furthered. Whilst consumed by actors in various class positions, a logic of distinction is present in white-collar boxing, which becomes recognisable through analysis of the ‘plurality of consumption experiences’. This is proffered as a concept which can aid in the analysis of consumption beyond white-collar boxing.

show abstract

“…Instead, he attributes it to the diversity of the stated preferences of people of the upper class, whereas the preferences of members of lower-status classes appear more exclusive. Later work, studying music taste in the "modern age" [51], found little evidence that musical taste is indeed aligned with class position.…”

Section: Conceptual Background and Related Workmentioning

confidence: 99%

Listener Modeling and Context-aware Music Recommendation Based on Country Archetypes

Schedl,

Bauer,

Reisinger

et al. 2020

Preprint

View full text Add to dashboard Cite

Music preferences are strongly shaped by the cultural and socio-economic background of the listener, which is reflected, to a considerable extent, in country-specific music listening profiles. Previous work has already identified several country-specific differences in the popularity distribution of music artists listened to. In particular, what constitutes the "music mainstream" strongly varies between countries. To complement and extend these results, the article at hand delivers the following major contributions: First, using state-ofthe-art unsupervised learning techniques, we identify and thoroughly investigate (1) country profiles of music preferences on the fine-grained level of music tracks (in contrast to earlier work that relied on music preferences on the artist level) and (2) country archetypes that subsume countries sharing similar patterns of listening preferences. Second, we formulate four user models that leverage the user's country information on music preferences. Among others, we propose a user modeling approach to describe a music listener as a vector of similarities over the identified country clusters or archetypes. Third, we propose a context-aware music recommendation system that leverages implicit user feedback, where context is defined via the four user models. More precisely, it is a multi-layer generative model based on a variational autoencoder, in which contextual features can influence recommendations through a gating mechanism. Fourth, we thoroughly evaluate the proposed recommendation system and user models on a real-world corpus of more than one billion listening records of users around the world (out of which we use 369 million in our experiments) and show its merits vis-à-vis state-of-the-art algorithms that do not exploit this type of context information.

show abstract

Beyond Class Stratification: The Rise of the Eclectic Music Consumer in the Modern Age

Cited by 6 publications

References 34 publications

Listener Modeling and Context-Aware Music Recommendation Based on Country Archetypes

Listener Modeling and Context-Aware Music Recommendation Based on Country Archetypes

On white-collar boxing and social class

Listener Modeling and Context-aware Music Recommendation Based on Country Archetypes

Contact Info

Product

Resources

About