deezer_friends — Deezer user friendships (2017, 2020)

Description

Social networks of users of the music streaming service Deezer, collected from its public API by B. Rozemberczki and collaborators for benchmarks of node embedding and classification methods. Nodes are users, and an undirected edge connects two users who are friends (follow each other). The users were reindexed for anonymity. There are two data sets:

GEMSEC (collected in November 2017): three networks of users from Croatia (HR), Hungary (HU) and Romania (RO). Each user has the list of music genres they like, compiled by the authors from the songs the user liked (84 distinct genres).
deezer_europe (FEATHER, collected in March 2020): a network of 28,281 users from European countries. Each user has a list of binary features, extracted from the artists liked by the user (only the indices of the features are given, not their meaning; 6,159 users have none), and a binary gender label, which the authors derived from the user's name; which value stands for which gender is not documented.

The networks have the following properties:

GEMSEC networks: genres, the list of music genres liked by the user (e.g. "Pop", "Rap/Hip Hop").
deezer_europe: gender, the binary gender label (stored as a Boolean: false and true for the labels 0 and 1 of the data); features, the indices of the user's binary features.

Tags

Social Online Unweighted Metadata

Citation

B. Rozemberczki, R. Davies, R. Sarkar, and C. Sutton, "GEMSEC: Graph Embedding with Self Clustering." Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), 65-72 (2019). 10.1145/3341161.3342890 Sci-Hub
B. Rozemberczki and R. Sarkar, "Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models." Proceedings of the 29th ACM International Conference on Information and Knowledge Management (CIKM), 1325-1334 (2020). 10.1145/3340531.3411866 Sci-Hub

Upstream URL OK

https://snap.stanford.edu/data/gemsec-Deezer.html
https://snap.stanford.edu/data/feather-deezer-social.html
https://github.com/benedekrozemberczki/datasets

Upstream license

MIT License, https://github.com/benedekrozemberczki/datasets/blob/3b19135105432cbca65765c1113b91c395ed9d44/LICENSE

Networks

Tip: click on a column header to sort the list, or hover over it for a description.

Column legend

$\left<k\right>$: Mean degree
$\sigma_k$: Standard deviation of the degrees
$\lambda_h$: Largest eigenvalue of the Hashimoto (non-backtracking) matrix
$\tau$: Random walk mixing time
$r$: Degree assortativity
$c$: Global clustering coefficient
$\oslash$: (Pseudo-) diameter
$S$: Relative size of the largest component
NPs: Node properties
EPs: Edge properties

Name	Nodes	Edges	$\left<k\right>$	$\sigma_k$	$\lambda_h$	$\tau$	$r$	$c$	$\oslash$	$S$	Kind	Mode	NPs	gt	GraphML	GML	csv
HR	54,573	498,202	18.26	17.95	46.19	30.02	0.20	0.11	12	1.00	Undirected	Unipartite	genres	1.3 MiB	2.2 MiB	2.2 MiB	2.4 MiB
HU	47,538	222,887	9.38	7.39	22.91	15.78	0.21	0.09	14	1.00	Undirected	Unipartite	genres	720 KiB	1.2 MiB	1.2 MiB	1.3 MiB
RO	41,773	125,826	6.02	5.51	15.97	52.38	0.11	0.08	19	1.00	Undirected	Unipartite	genres	490 KiB	805 KiB	800 KiB	895 KiB
deezer_europe	28,281	92,752	6.56	7.95	23.01	333.61	0.10	0.10	21	1.00	Undirected	Unipartite	features gender	1.6 MiB	1.9 MiB	1.9 MiB	2.8 MiB