Wikipedia talk (es)
This is the communication network of the Spanish Wikipedia. Nodes represent
users, and an edge from user A to user B denotes that user A wrote a message on
the talk page of user B at a certain timestamp.
Metadata
Statistics
Size | n = | 497,446
|
Volume | m = | 2,702,879
|
Unique edge count | m̿ = | 1,250,097
|
Loop count | l = | 310,456
|
Wedge count | s = | 36,007,011,621
|
Claw count | z = | 2,134,034,493,823,165
|
Triangle count | t = | 2,521,702
|
Square count | q = | 17,513,494,039
|
4-Tour count | T4 = | 284,138,127,786
|
Maximum degree | dmax = | 373,874
|
Maximum outdegree | d+max = | 373,873
|
Maximum indegree | d−max = | 23,514
|
Average degree | d = | 10.867 0
|
Fill | p = | 5.051 87 × 10−6
|
Average edge multiplicity | m̃ = | 2.162 14
|
Size of LCC | N = | 476,465
|
Diameter | δ = | 10
|
50-Percentile effective diameter | δ0.5 = | 2.720 21
|
90-Percentile effective diameter | δ0.9 = | 3.744 94
|
Median distance | δM = | 3
|
Mean distance | δm = | 3.223 73
|
Gini coefficient | G = | 0.819 217
|
Balanced inequality ratio | P = | 0.165 433
|
Outdegree balanced inequality ratio | P+ = | 0.078 457 8
|
Indegree balanced inequality ratio | P− = | 0.262 955
|
Relative edge distribution entropy | Her = | 0.732 569
|
Power law exponent | γ = | 2.774 01
|
Tail power law exponent | γt = | 1.781 00
|
Degree assortativity | ρ = | −0.234 987
|
Degree assortativity p-value | pρ = | 0.000 00
|
Clustering coefficient | c = | 0.000 210 101
|
Directed clustering coefficient | c± = | 0.027 027 9
|
Spectral norm | α = | 7,538.02
|
Operator 2-norm | ν = | 3,800.41
|
Algebraic connectivity | a = | 0.042 304 4
|
Spectral separation | |λ1[A] / λ2[A]| = | 1.162 15
|
Reciprocity | y = | 0.250 041
|
Non-bipartivity | bA = | 0.761 780
|
Normalized non-bipartivity | bN = | 0.017 255 3
|
Algebraic non-bipartivity | χ = | 0.043 537 3
|
Spectral bipartite frustration | bK = | 0.002 352 25
|
Controllability | C = | 433,355
|
Relative controllability | Cr = | 0.871 160
|
Plots
Matrix decompositions plots
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]
|
Jun Sun, Jérôme Kunegis, and Steffen Staab.
Predicting user roles in social networks using transfer learning with
feature transformation.
In Proc. ICDM Workshop on Data Min. in Netw., 2016.
|