Abstract
Music recommendation systems have become an important part of the user-centric online music listening experience. However, current automated systems often are not tuned for exploiting the full diversity of a song catalogue, and consequently, discovering new music requires considerable user effort. Another issue is current implementations generally require significant artist metadata, user listening history, or a combination of the two, to generate relevant recommendations. To address the problems with traditional recommendation systems, we propose to represent artist-to-artist relationships as both simple multigraphs and more complicated multidimensional networks. Using data gathered from the MusicBrainz open music encyclopedia, we demonstrate our artist-based networks are capable of producing more diverse and relevant artist recommendations.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
M. Schedl, P. Knees, B. McFee, et al., Music recommender systems, in Recommender systems handbook, ed. by F. Ricci, L. Rokach, B. Shapira, (Springer, Boston, 2015), pp. 453–492
M. Schedl, H. Zamani, C.W. Chen, et al., Current challenges and visions in music recommender systems research. Int J Multimedia Inf Retr 7(2), 95–116 (2018)
A. Vall, M. Dorfer, H. Eghbal-zadeh, et al., Feature-combination hybrid recommender systems for automated music playlist continuation. User Model. User-Adap. Inter. 29, 527–572 (2019). https://doi.org/10.1007/s11257-018-9215-8
A. Van den Oord, S. Dieleman, B. Schrauwen, Deep content-based music recommendation, in Proceedings of the 26th International Conference on Neural Information Processing Systems (NIPS’13), (December 2013), pp. 2643–2651
Ã’. Celma, Music Recommendation and Discovery in the Long Tail, Dissertation, Universitat Pompeu Fabra, Barcelona, Spain, 2008
K. Mao, G. Chen, Y. Hu, L. Zhang, Music recommendation using graph based quality model. Signal Process. 120, 806–813 (2015). https://doi.org/10.1016/j.sigpro.2015.03.026
D. Zhao, L. Zhang, W. Zhao, Genre-based link prediction in bipartite graph for music recommendation. Procedia Comput. Sci. 91, 959–965 (2016)
A. Tiroshi, T. Kuflik, S. Berkovsky, M.A. Kaafar, Graph based recommendations: From data representation to feature extraction and application, in Big Data Recommender Systems, ed. by O. Khalid, S. U. Khan, A. Y. Zomaya, vol. 2, (IET, Stevenage, 2019), pp. 407–454
L. Zhang, M. Zhao, D. Zhao, Bipartite graph link prediction method with homogeneous nodes similarity for music recommendation. Multimed. Tools Appl. (2020). https://doi.org/10.1007/s11042-019-08451-x
MusicBrainz Database, MetaBrainz Foundation, California (2019), https://musicbrainz.org/doc/MusicBrainz_Database. Accessed 14 May 2020
S. Boccaletti, G. Bianconi, R. Criado, et al., The structure and dynamics of multilayer networks. Phys. Rep. 544(1), 1–122 (2014)
T.H. Cormen, C.E. Leiserson, R.L. Rivest, C. Stein, Introduction to Algorithms, 3rd edn. (The MIT press, Cambridge, MA/London, 2009)
MusicBrainz, The Who: Tags (2019), https://musicbrainz.org/artist/9fdaa16b-a6c4-4831-b87c-bc9ca8ce7eaa/tags. Accessed 14 May 2020
A. Hagberg, D. Schult, P. Swart, Exploring network structure, dynamics, and function using NetworkX, in Proceedings of the 7th Python in Science Conference (SciPy), (Pasadena, California, August 2008), pp. 11–15
N. Perra, S. Fortunato, Spectral centrality measures in complex networks. Phys. Rev. E 78(3 Pt 2), 036107 (2008)
S.Y. Chou, Y.H. Yang, Y.C. Lin, Evaluating music recommendation in a real-world setting: On data splitting and evaluation metrics, in The 2015 IEEE International Conference on Multimedia and Expo (ICME), (Turin, Italy, August 2015), pp. 1–6
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix A: Comparison of Three Node Importance Measurements in Two Multigraphs
Appendix A: Comparison of Three Node Importance Measurements in Two Multigraphs
Rank | Graph I with The Who, The Rolling Stones, Van Halen, The Eagles, and Boston as seed artists | Graph II with R.E.M., Spice Girls, Megadeth, The Cardigans, and Abba as seed artists | ||||||
Artist | Degree centrality | Load centrality | Page rank | Artist | Degree centrality | Load centrality | Page rank | |
1 | Black | 4.181 | 0.038 | 0.011 | Metallica | 2.441 | 0.007 | 0.007 |
2 | The Rolling Stones | 3.598 | 0.046 | 0.010 | Black Sabbath | 2.568 | 0.008 | 0.007 |
3 | Genesis | 4.098 | 0.018 | 0.010 | R.E.M. | 2.047 | 0.056 | 0.007 |
4 | Whitesnake | 3.960 | 0.016 | 0.010 | The Smiths | 2.453 | 0.010 | 0.007 |
5 | Yes | 4.014 | 0.009 | 0.009 | Motörhead | 2.378 | 0.008 | 0.007 |
6 | Deep Purple | 3.768 | 0.014 | 0.009 | Whitesnake | 2.408 | 0.008 | 0.007 |
7 | Queen | 3.691 | 0.013 | 0.009 | Megadeth | 1.676 | 0.043 | 0.007 |
8 | Alice Cooper | 3.443 | 0.018 | 0.008 | Queen | 2.319 | 0.012 | 0.006 |
9 | The Who | 3.248 | 0.027 | 0.008 | The Pretenders | 2.371 | 0.003 | 0.006 |
10 | Electric Light Orchestra | 3.640 | 0.004 | 0.008 | Ozzy Osbourne | 2.286 | 0.010 | 0.006 |
11 | Ozzy Osbourne | 3.394 | 0.014 | 0.008 | The Damned | 2.029 | 0.021 | 0.006 |
12 | Artists united against apartheid | 0.973 | 0.064 | 0.008 | Alice Cooper | 2.180 | 0.009 | 0.006 |
13 | Uriah Heep | 3.520 | 0.003 | 0.008 | New Order | 2.221 | 0.006 | 0.006 |
14 | Eric Clapton | 3.547 | 0.003 | 0.008 | Simple Minds | 2.209 | 0.003 | 0.006 |
15 | The Kinks | 3.549 | 0.003 | 0.008 | Fleetwood Mac | 2.185 | 0.006 | 0.006 |
16 | Frank Zappa | 3.242 | 0.010 | 0.008 | Killing Joke | 2.082 | 0.007 | 0.006 |
17 | The Yardbirds | 3.229 | 0.009 | 0.008 | The Who | 1.985 | 0.010 | 0.006 |
18 | Santana | 3.056 | 0.009 | 0.007 | Ac/Dc | 1.965 | 0.005 | 0.005 |
19 | Brian May | 3.152 | 0.004 | 0.007 | The Lightning Seeds | 1.980 | 0.005 | 0.005 |
Rank | Graph I with The Who, The Rolling Stones, Van Halen, The Eagles, and Boston as seed artists | Graph II with R.E.M., Spice Girls, Megadeth, The Cardigans, and Abba as seed artists | ||||||
Artist | Degree centrality | Load centrality | Page rank | Artist | Degree centrality | Load centrality | Page rank | |
20 | Faces | 2.853 | 0.016 | 0.007 | Oasis | 1.908 | 0.007 | 0.005 |
21 | Boston | 2.899 | 0.014 | 0.007 | Tool | 1.882 | 0.005 | 0.005 |
22 | Def Leppard | 3.046 | 0.004 | 0.007 | The Hollies | 1.934 | 0.004 | 0.005 |
23 | The Beach Boys | 3.166 | 0.002 | 0.007 | Radiohead | 1.839 | 0.008 | 0.005 |
24 | Van Halen | 2.672 | 0.023 | 0.007 | Nine Inch Nails | 1.786 | 0.006 | 0.005 |
25 | Jethro Tull | 3.061 | 0.004 | 0.007 | Modest Mouse | 1.456 | 0.026 | 0.005 |
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Waggoner, J., Dunkleman, R., Gao, Y., Gary, T., Wang, Q. (2021). A Multigraph-Based Method for Improving Music Recommendation. In: Arabnia, H.R., Ferens, K., de la Fuente, D., Kozerenko, E.B., Olivas Varela, J.A., Tinetti, F.G. (eds) Advances in Artificial Intelligence and Applied Cognitive Computing. Transactions on Computational Science and Computational Intelligence. Springer, Cham. https://doi.org/10.1007/978-3-030-70296-0_47
Download citation
DOI: https://doi.org/10.1007/978-3-030-70296-0_47
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-70295-3
Online ISBN: 978-3-030-70296-0
eBook Packages: Computer ScienceComputer Science (R0)