Using personalized radio to enhance local music discovery

Turnbull, Douglas; Zupnick, Justin Adam; Stensland, Kristofer B.; Horwitz, Andrew R.; Wolf, Alexander J.; Spirgel, Alexander E.; Meyerhofer, Stephen P.; Joachims, Thorsten

doi:10.1145/2559206.2581246

Cited by 12 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To date, the social computing community has examined online listening activity as source of information and recommendations for music (Bu et al 2010;Zheleva et al 2010;Farrahi et al 2014;Turnbull et al 2014). However, computational tools and online outlets such as social media can make further contributions toward understanding human behavior related to musical consumption and help to elaborate user-centric music retrieval systems by analyzing personal characteristics.…”

Section: Introductionmentioning

confidence: 99%

Understanding Musical Diversity via Online Social Media

Park

Weber²,

Нааман

et al. 2021

ICWSM

View full text Add to dashboard Cite

Musicologists and sociologists have long been interested in patterns of music consumption and their relation to socioeconomic status. In particular, the Omnivore Thesis examines the relationship between these variables and the diversity of music a person consumes. Using data from social media users of Last.fm and Twitter, we design and evaluate a measure that reasonably captures diversity of musical tastes. We use that measure to explore associations between musical diversity and variables that capture socioeconomic status, demographics, and personal traits such as openness and degree of interest in music (into-ness). Our musical diversity measure can provide a useful means for studies of musical preferences and consumption. Also, our study of the Omnivore Thesis provides insights that extend previous survey and interview-based studies.

show abstract

Section: Introductionmentioning

confidence: 99%

Understanding Musical Diversity via Online Social Media

Park

Weber²,

Нааман

et al. 2021

ICWSM

View full text Add to dashboard Cite

show abstract

“…Odom and Duel have contributed the OLO radio design artifact that allows people to explore and (re-)experience the music that they have listened to over the course of their lives [42]. Turnbull et al have found that personalized radio can help to stimulate the discovery of local music and local musical events [55]. Casagranda et al have proposed Hybrid Content Radio (HCR), which combines linear radio with OTT delivery of personalized audio content [7].…”

Section: Background and Related Workmentioning

confidence: 99%

Stay Tuned! An Investigation of Content Substitution, the Listener as Curator and Other Innovations in Broadcast Radio

Wijnants

Geurts

Lievens

et al. 2021

ACM International Conference on Interactive Media Experiences

View full text Add to dashboard Cite

This paper demystifes listeners' wishes with respect to broadcast radio innovation (with a specifc focus on radio-mediated music consumption). Our study encompasses an ideation workshop with radio experts, an exploratory survey and a mixed methods empirical evaluation. The empirical evaluation uses two concrete concepts (i.e., letting listeners on-the-fy replace radio content with preferred content and fostering participatory radio production by involving listeners as radio content curators) as a lens to zoom in on the questionable desirability of radio innovation. It is learned that a signifcant consumer group exists who will stay loyal to broadcast radio even if it does not evolve substantially, whereas others need disruptive incentives to start listening to radio (again). From our results we distill design recommendations to educate the radio production community about how best to approach radio innovation. CCS CONCEPTS• Information systems → Multimedia streaming; • Humancentered computing → Laboratory experiments; User studies.

show abstract

“…Latent Markov Embedding: Latent Markov Embedding (LME) [10,11,13,58,63] was recently proposed to tractably learn trajectories through a Markov chain whose states are projected user trajectories into Euclidean space. However, even with parallel optimizations [11] the method does not yet scaled beyond hundreds of thousands of users and items (as shown in Section 4.3).…”

Section: Related Workmentioning

confidence: 99%

TribeFlow

Figueiredo

Ribeiro

Almeida

et al. 2016

Proceedings of the 25th International Conference on World Wide Web

View full text Add to dashboard Cite

Which song will Smith listen to next? Which restaurant will Alice go to tomorrow? Which product will John click next? These applications have in common the prediction of user trajectories that are in a constant state of flux over a hidden network (e.g. website links, geographic location). But what users are doing now may be unrelated to what they will be doing in an hour from now. Mindful of these challenges we propose TribeFlow, a method designed to cope with the complex challenges of learning personalized predictive models of non-stationary, transient, and time-heterogeneous user trajectories. TribeFlow is a general method that can perform next product recommendation, next song recommendation, next location prediction, and general arbitrary-length user trajectory prediction without domain-specific knowledge. TribeFlow is more accurate and up to 413× faster than top competitors.

show abstract

Using personalized radio to enhance local music discovery

Cited by 12 publications

References 7 publications

Understanding Musical Diversity via Online Social Media

Understanding Musical Diversity via Online Social Media

Stay Tuned! An Investigation of Content Substitution, the Listener as Curator and Other Innovations in Broadcast Radio

TribeFlow

Contact Info

Product

Resources

About