youtube_interactions — YouTube user interactions, multi-dimensional (2008)

Description

Five networks of different kinds of interactions among the same set of YouTube users, crawled in December 2008 by L. Tang, X. Wang and H. Liu (Arizona State University), and distributed by the Social Computing Data Repository (originally at Arizona State University, now at Syracuse University). Starting from the authors of 100 recently uploaded videos, the crawl collected the contacts, subscriptions and favourite videos of 30,522 user profiles, reaching 848,003 users and 1,299,642 videos in total; the 15,088 users sharing all kinds of information were retained. In all networks, nodes are these 15,088 users (users without interactions of a given kind are isolated nodes), and an undirected edge connects two users that interact in the given way, with weight giving the intensity of the interaction:

contacts: the two users are contacts of each other (weight 1).
shared_friends: the two users have contacts in common, among the 848,003 users outside the set; weight is the number of shared contacts (at least 2).
shared_subscriptions: the two users subscribe to the same users; weight is the number of shared subscriptions.
shared_subscribers: the two users have subscribers in common; weight is the number of shared subscribers.
shared_favorites: the two users marked the same videos as favourites; weight is the number of shared favourite videos (at least 2).

The networks have the following properties:

weight: the intensity of the interaction.

Tags

Social Online Weighted Multilayer

Citation

L. Tang, X. Wang, H. Liu, "Uncovering groups via heterogeneous interaction analysis." Ninth IEEE International Conference on Data Mining (ICDM), 503-512 (2009) 10.1109/ICDM.2009.20 Sci-Hub
L. Tang, X. Wang, H. Liu, "Community detection via heterogeneous interaction analysis." Data Mining and Knowledge Discovery 25, 1-33 (2012) 10.1007/s10618-011-0231-0 Sci-Hub

Upstream URL OK

https://datasets.syr.edu/

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	EPs	gt	GraphML	GML	csv
contacts	15,088	76,765	10.18	18.81	55.05	45.82	-0.08	0.08	12	0.91	Undirected	Unipartite	weight	139 KiB	268 KiB	263 KiB	269 KiB
shared_friends	15,088	1,940,806	257.26	379.99	897.61	50.99	0.14	0.42	9	0.88	Undirected	Unipartite	weight	1.8 MiB	6.3 MiB	6.2 MiB	5.4 MiB
shared_subscriptions	15,088	5,574,249	738.90	983.58	2021.17	3.56	-0.07	0.47	6	0.78	Undirected	Unipartite	weight	3.4 MiB	16.6 MiB	16.1 MiB	14.8 MiB
shared_subscribers	15,088	2,239,440	296.85	482.81	1147.02	7.12	-0.02	0.42	6	0.69	Undirected	Unipartite	weight	1.5 MiB	6.6 MiB	6.6 MiB	5.9 MiB
shared_favorites	15,088	3,797,635	503.40	789.51	1679.98	8.96	-0.12	0.40	7	0.87	Undirected	Unipartite	weight	4.0 MiB	12.7 MiB	12.1 MiB	10.9 MiB