Auralist: introducing serendipity into music recommendation

@inproceedings{Zhang2012AuralistIS,
  title={Auralist: introducing serendipity into music recommendation},
  author={Y. Zhang and Diarmuid {\'O} S{\'e}aghdha and D. Quercia and T. Jambor},
  booktitle={WSDM '12},
  year={2012}
}
Recommendation systems exist to help users discover content in a large body of items. [...] Key Method Using a collection of novel algorithms inspired by principles of "serendipitous discovery", we demonstrate a method of successfully injecting serendipity, novelty and diversity into recommendations whilst limiting the impact on accuracy. We evaluate Auralist quantitatively over a broad set of metrics and, with a user study on music recommendation, show that Auralist's emphasis on serendipity indeed improves…Expand
262 Citations

Figures, Tables, and Topics from this paper

Music recommenders based on hybrid techniques and serendipity
  • 3
A Serendipity Model for News Recommendation
  • 16
  • PDF
A model for serendipitous music retrieval
  • 29
  • PDF
Tailoring Music Recommendations to Users by Considering Diversity, Mainstreaminess, and Novelty
  • 41
  • PDF
HAES: A New Hybrid Approach for Movie Recommendation with Elastic Serendipity
  • 5
  • PDF
Evaluating Hybrid Music Recommender Systems
  • 22
An investigation on the serendipity problem in recommender systems
  • 77
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 10 REFERENCES
Improving recommendation lists through topic diversification
  • 1,541
  • Highly Influential
  • PDF
Beyond Algorithms: An HCI Perspective on Recommender Systems
  • 309
  • Highly Influential
Collaborative Filtering for Implicit Feedback Datasets
  • 2,267
  • Highly Influential
  • PDF
Toward more diverse recommendations: Item re-ranking methods for recommender systems
  • 50
  • Highly Influential
  • PDF
Solving the apparent diversity-accuracy dilemma of recommender systems
  • 707
  • Highly Influential
  • PDF
Rank and relevance in novelty and diversity metrics for recommender systems
  • 467
  • Highly Influential
  • PDF
Evaluating collaborative filtering recommender systems
  • 5,276
  • Highly Influential
  • PDF
Finding scientific topics
  • T. Griffiths, M. Steyvers
  • Computer Science, Medicine
  • Proceedings of the National Academy of Sciences of the United States of America
  • 2004
  • 4,978
  • Highly Influential
  • PDF
Latent Dirichlet Allocation
  • 26,278
  • Highly Influential
  • PDF
Choosing less-preferred experiences for the sake of variety.
  • 457
  • Highly Influential