(also spelled Líbí; from Czech Líbím se ti, "Do you like me") is a Czech dating site. This is the network of ratings given by users of to other users. The network is unipartite, directed, and edges represent ratings on a scale from 1 to 10.


Internal namelibimseti
Data source
AvailabilityDataset is available for download
Consistency checkDataset passed all tests
Online social network
Node meaningUser
Edge meaningRating
Network formatUnipartite, directed
Edge typeRatings, no multiple edges
ReciprocalContains reciprocal edges
Directed cyclesContains directed cycles
LoopsDoes not contain loops


Size n =220,970
Volume m =17,359,346
Wedge count s =28,261,600,655
Claw count z =82,085,727,142,249
Cross count x =328,616,649,550,852,928
Triangle count t =69,115,603
Square count q =252,125,304,066
4-Tour count T4 =2,130,083,301,436
Maximum degree dmax =33,389
Maximum outdegree d+max =25,042
Maximum indegree dmax =33,389
Average degree d =157.119
Fill p =0.000 355 524
Size of LCC N =220,970
Size of LSCC Ns =81,145
Relative size of LSCC Nrs =0.367 222
Diameter δ =6
50-Percentile effective diameter δ0.5 =2.383 02
90-Percentile effective diameter δ0.9 =3.088 97
Mean distance δm =2.853 61
Gini coefficient G =0.710 031
Relative edge distribution entropy Her =0.905 698
Power law exponent γ =1.267 38
Tail power law exponent γt =1.911 00
Degree assortativity ρ =−0.138 967
Degree assortativity p-value pρ =0.000 00
In/outdegree correlation ρ± =−0.053 936 3
Clustering coefficient c =0.007 336 70
Spectral norm α =1,127.41
Operator 2-norm ν =1,091.14
Cyclic eigenvalue π =180.755
Spectral separation 1[A] / λ2[A]| =1.048 45
Reciprocity y =0.014 539 9
Non-bipartivity bA =0.167 400
Normalized non-bipartivity bN =0.133 489
Negativity ζ =0.478 986
Algebraic conflict ξ =0.335 197
Triadic conflict τ =0.523 841
Spectral signed frustration φ =0.000 537 773


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

Zipf plot

Hop distribution

In/outdegree scatter plot

Item rating evolution

Edge weight/multiplicity distribution

Clustering coefficient distribution


Matrix decompositions plots



[1] Jérôme Kunegis. KONECT – The Koblenz Network Collection. In Proc. Int. Conf. on World Wide Web Companion, pages 1343–1350, 2013. [ http ]
[2] Jérôme Kunegis, Gerd Gröner, and Thomas Gottron. Online dating recommender systems: The split-complex number approach. In Proc. RecSys Workshop on Recomm. Syst. and the Soc. Web, pages 37–44, 2012.
[3] Lukáš Brožovský and Václav Petříček. Recommender system for online dating service. In Proc. Znalosti, pages 29–40, 2007.