Wikipedia talk (eo)
This is the communication network of the Esperanto 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 = | 7,586
|
Volume | m = | 47,070
|
Unique edge count | m̿ = | 17,362
|
Loop count | l = | 9,827
|
Wedge count | s = | 6,334,328
|
Claw count | z = | 3,412,850,433
|
Cross count | x = | 1,415,995,053,128
|
Triangle count | t = | 18,044
|
Square count | q = | 2,062,111
|
4-Tour count | T4 = | 41,862,732
|
Maximum degree | dmax = | 5,157
|
Maximum outdegree | d+max = | 3,540
|
Maximum indegree | d−max = | 2,380
|
Average degree | d = | 12.409 7
|
Fill | p = | 0.000 301 699
|
Average edge multiplicity | m̃ = | 2.711 09
|
Size of LCC | N = | 7,253
|
Size of LSCC | Ns = | 822
|
Relative size of LSCC | Nrs = | 0.108 358
|
Diameter | δ = | 8
|
50-Percentile effective diameter | δ0.5 = | 2.575 43
|
90-Percentile effective diameter | δ0.9 = | 3.630 51
|
Median distance | δM = | 3
|
Mean distance | δm = | 3.095 16
|
Gini coefficient | G = | 0.865 440
|
Balanced inequality ratio | P = | 0.132 813
|
Outdegree balanced inequality ratio | P+ = | 0.102 549
|
Indegree balanced inequality ratio | P− = | 0.194 370
|
Relative edge distribution entropy | Her = | 0.758 358
|
Power law exponent | γ = | 3.047 78
|
Tail power law exponent | γt = | 2.031 00
|
Tail power law exponent with p | γ3 = | 2.031 00
|
p-value | p = | 0.013 000 0
|
Outdegree tail power law exponent with p | γ3,o = | 2.011 00
|
Outdegree p-value | po = | 0.000 00
|
Indegree tail power law exponent with p | γ3,i = | 2.211 00
|
Indegree p-value | pi = | 0.184 000
|
Degree assortativity | ρ = | −0.423 923
|
Degree assortativity p-value | pρ = | 0.000 00
|
In/outdegree correlation | ρ± = | +0.715 506
|
Clustering coefficient | c = | 0.008 545 82
|
Directed clustering coefficient | c± = | 0.056 901 0
|
Spectral norm | α = | 1,762.80
|
Operator 2-norm | ν = | 889.457
|
Cyclic eigenvalue | π = | 871.028
|
Algebraic connectivity | a = | 0.101 624
|
Spectral separation | |λ1[A] / λ2[A]| = | 1.422 85
|
Reciprocity | y = | 0.279 058
|
Non-bipartivity | bA = | 0.753 769
|
Normalized non-bipartivity | bN = | 0.056 411 3
|
Algebraic non-bipartivity | χ = | 0.100 022
|
Spectral bipartite frustration | bK = | 0.005 931 62
|
Controllability | C = | 6,049
|
Relative controllability | Cr = | 0.797 390
|
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.
|