From hits to niches?: or how popular artists can bias music recommendation and discovery
By Òscar Celma, Pedro Cano. 2008
206 citations recorded by the source corpus.
Subfields: Statistical and Nonlinear Physics, Signal Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Statistical and Nonlinear Physics
- Noam Koenigstein
- Bamshad Mobasher
- Yehuda Koren
- Dietmar Jannach
- Paolo Cremonesi
- Robin D. Burke
- Barbara E. Engelhardt
- Gideon Dror
In Signal Processing
- Dietmar Jannach
- Bamshad Mobasher
- Paolo Cremonesi
- Noam Koenigstein
- Yehuda Koren
- Gediminas Adomavicius
- Robin D. Burke
- Barbara E. Engelhardt
Citations in the corpus
- How algorithmic confounding in recommendation systems increases homogeneity and decreases utility (2017, methodology): “Many eorts have been made to understand whether or not various recommender systems impact diversity by reinforcing the popularity of already-popular products or by increasing interactions with niche items [2, 11, 15, 20, 47, 63].”
- Multistakeholder recommendation: Survey and research directions (2020, background): “the in uence of specic information. We give several examples. Enhancing fairness is useful for correcting a popularity bias, which is the tendency for popular items to be recommended more frequently [29]. If users are already familiar with the popular items and are seeking minor and longtail items t”
- Auralist: introducing serendipity into music recommendation (2012, background): “[5, 4] to investigate the long-tail properties of music recommendation in terms of network links.”
- Recommendations : Modeling Music Ratings with Temporal Dynamics and Item Taxonomy (2011, background): “niques suffer from a cold-start problem in many of the less popular artists in the “long tail” [7].”
- Performance of recommender algorithms on top-n recommendation tasks (2010, background): “as the short-head, and to the remaining set of less popular items – about 98% of the total – as the long-tail [5].”
- Controlling Popularity Bias in Learning-to-Rank Recommendation (2017, background): “A market that suffers from popularity bias will lack opportunities to discover more obscure products and will be, by definition, dominated by a few large brands or well-known artists [6].”