Yahoo songs

This is the bipartite person–song rating network used in the KDD Cup 2011. It contains ratings on a scale from 0 to 100 taken from Yahoo Music. This network contains over 250 million edges (i.e., ratings), and is one of the largest openly-available rating datasets.

Metadata

CodeYS
Internal nameyahoo-song
NameYahoo songs
Data sourcehttp://www.kdnuggets.com/2011/02/kdd-cup-2011-recommending-music.html
AvailabilityDataset is available for download
Consistency checkDataset passed all tests
Category
Rating network
Node meaningPerson, song
Edge meaningRating
Network formatBipartite, undirected
Edge typeRatings, no multiple edges
Temporal data Edges are annotated with timestamps

Statistics

Size n =1,625,951
Left size n1 =1,000,990
Right size n2 =624,961
Volume m =256,804,235
Wedge count s =4,627,224,528,654
Maximum degree dmax =468,366
Maximum left degree d1max =307,205
Maximum right degree d2max =468,366
Average degree d =315.882
Average left degree d1 =256.550
Average right degree d2 =410.912
Fill p =0.000 410 506
Size of LCC N =1,625,951
50-Percentile effective diameter δ0.5 =2.236 31
90-Percentile effective diameter δ0.9 =3.350 05
Mean distance δm =2.760 80
Gini coefficient G =0.752 830
Balanced inequality ratio P =0.201 029
Left balanced inequality ratio P1 =0.192 464
Right balanced inequality ratio P2 =0.163 685
Relative edge distribution entropy Her =0.871 153
Power law exponent γ =1.403 07
Degree assortativity ρ =−0.103 038
Degree assortativity p-value pρ =0.000 00
Spectral norm α =130,625
Negativity ζ =0.541 386

Plots

Degree distribution

Cumulative degree distribution

Lorenz curve

Spectral distribution of the adjacency matrix

Spectral distribution of the normalized adjacency matrix

Spectral distribution of the Laplacian

Spectral graph drawing based on the adjacency matrix

Spectral graph drawing based on the normalized adjacency matrix

Degree assortativity

Hop distribution

Edge weight/multiplicity distribution

Temporal distribution

Diameter/density evolution

Signed temporal distribution

Downloads

References

[1] Jérôme Kunegis. KONECT – The Koblenz Network Collection. In Proc. Int. Conf. on World Wide Web Companion, pages 1343–1350, 2013. [ http ]
[2] Gideon Dror, Noam Koenigstein, Yehuda Koren, and Markus Weimer. The Yahoo! Music dataset and KDD-Cup'11. In JMLR Workshop and Conf. Proc., volume 18, pages 3–18, 2012.