logo Netzschleuder network catalog, repository, and centrifuge

aminer_social_influence — AMiner social influence data sets: coauthorships, citations and movies (2009)

Description

Networks released by J. Tang and colleagues (Tsinghua University) with their study of topic-based social influence analysis, extracted from the AMiner (ArnetMiner) academic search system and from Wikipedia. The academic networks cover research topics found by an author-conference-topic model of AMiner: 16 (Data Mining / Association Rules), 24 (Database Systems / XML Data), 75 (Information Retrieval), 107 (Web Services), 131 (Bayesian Networks / Belief Function), 144 (Web Mining / Information Fusion), 145 (Semantic Web / Description Logics), 162 (Machine Learning), 182 (Pattern Recognition / Image Analysis) and 199 (Natural Language Systems / Statistical Machine Translation).

  • coauthors_T<topic>_sub<k>: coauthorship networks of the authors of a topic (topics 16, 24, 75, 107, 131, 144, 145 and 162; for some topics there are several separate networks, numbered by k). Nodes are authors, and an undirected edge connects two authors who coauthored papers, with weight equal to the number of coauthored papers.
  • citations_T<topic>: citation networks of the papers of a topic (all ten topics). Nodes are papers, and a directed edge connects two papers with a citation relationship. The direction is not documented for these networks; in citations_all, where publication years are available, the source paper is the later one for most edges, so that an edge presumably goes from the citing to the cited paper.
  • citations_all: a citation network of 2,555 papers of the ten topics (6,101 citations) with paper metadata. A directed edge goes from the source to the target paper of a citation relationship (see above).
  • movies: a network of the English-language films on Wikipedia and their actors ("starring"), directors and writers. Nodes are films and persons, and an undirected edge connects two nodes whose names appear on the same Wikipedia page. Some pairs are listed several times (kept as parallel edges), and some edges are self-loops.

The networks have the following properties:

  • (Node) name (coauthors, movies): the name of the author, film or person.
  • (Node) papers (coauthors): the number of papers of the author.
  • (Edge) weight (coauthors): the number of coauthored papers.
  • (Node) title (citations): the title of the paper.
  • (Node) cited (citations_T<topic>): the number of citations of the paper.
  • (Node) year, venue, authors (citations_all): the year of publication, publication venue and authors of the paper.
  • (Node) type (movies): the kind of node: "movie", "starring" (actor), "director" or "writer".
  • (Node) words (movies): the number of words introducing the node on Wikipedia.
  • (Node) categories (movies): the Wikipedia categories of the page of the node.

According to the source, the data are for research purposes only.

Tags
Social Collaboration Informational Citation Weighted Multigraph Metadata
Added
2026-10-25
Citation
  • J. Tang, J. Sun, C. Wang, Z. Yang, "Social influence analysis in large-scale networks." Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 807-816 (2009) 10.1145/1557019.1557108 Sci-Hub
  • J. Tang, J. Zhang, L. Yao, J. Li, L. Zhang, Z. Su, "ArnetMiner: extraction and mining of academic social networks." Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 990-998 (2008) 10.1145/1401890.1402008 Sci-Hub
Upstream URL OK
https://web.archive.org/web/20150115063659/http://arnetminer.org/lab-datasets/soinf/
https://lfs.aminer.cn/lab-datasets/soinf/
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 EPs gt GraphML GML csv
coauthors_T16_sub0 679 1,687 4.97 5.65 13.04 35.19 0.12 0.21 14 1.00 Undirected Unipartite name papers weight 23 KiB 33 KiB 32 KiB 25 KiB
coauthors_T24_sub0 1,127 6,690 11.87 14.88 36.89 25.71 0.21 0.23 11 1.00 Undirected Unipartite name papers weight 44 KiB 68 KiB 67 KiB 54 KiB
coauthors_T75_sub0 657 1,907 5.81 7.63 23.58 77.04 0.36 0.36 14 1.00 Undirected Unipartite name papers weight 23 KiB 32 KiB 32 KiB 25 KiB
coauthors_T75_sub5 7 7 2.00 0.76 1.00 4.83 -0.17 0.33 4 1.00 Undirected Unipartite name papers weight 1 KiB 2 KiB 1 KiB 2 KiB
coauthors_T107_sub1 400 777 3.88 3.77 8.33 39.18 0.14 0.24 14 1.00 Undirected Unipartite name papers weight 14 KiB 19 KiB 18 KiB 15 KiB
coauthors_T107_sub34 7 7 2.00 1.07 1.00 2.89 -0.38 0.27 4 1.00 Undirected Unipartite name papers weight 1 KiB 2 KiB 1 KiB 2 KiB
coauthors_T131_sub0 554 1,238 4.47 6.35 21.24 50.03 0.32 0.43 14 1.00 Undirected Unipartite name papers weight 19 KiB 26 KiB 26 KiB 20 KiB
coauthors_T144_sub4 348 595 3.42 2.98 7.25 80.38 0.17 0.31 14 1.00 Undirected Unipartite name papers weight 12 KiB 17 KiB 16 KiB 13 KiB
coauthors_T144_sub6 11 10 1.82 1.19 1.00 7.86 -0.50 0.00 5 1.00 Undirected Bipartite name papers weight 2 KiB 2 KiB 2 KiB 2 KiB
coauthors_T144_sub27 9 13 2.89 1.66 2.38 2.61 -0.47 0.49 3 1.00 Undirected Unipartite name papers weight 2 KiB 2 KiB 2 KiB 2 KiB
coauthors_T145_sub0 671 2,237 6.67 8.06 18.92 42.41 0.21 0.25 11 1.00 Undirected Unipartite name papers weight 24 KiB 34 KiB 34 KiB 27 KiB
coauthors_T145_sub196 10 15 3.00 1.34 2.37 4.86 -0.18 0.54 4 1.00 Undirected Unipartite name papers weight 2 KiB 2 KiB 2 KiB 2 KiB
coauthors_T162_sub1 976 2,293 4.70 5.19 11.13 49.58 0.09 0.17 13 0.94 Undirected Unipartite name papers weight 32 KiB 45 KiB 43 KiB 35 KiB
citations_T16 235 451 1.92 4.59 10.54 7.23 0.13 0.24 7 0.52 Directed Unipartite title cited 11 KiB 15 KiB 14 KiB 12 KiB
citations_T24 1,416 4,176 2.95 6.30 12.76 33.01 0.03 0.19 12 0.95 Directed Unipartite title cited 60 KiB 78 KiB 77 KiB 70 KiB
citations_T75 93 112 1.20 2.06 3.25 51.75 -0.21 0.11 11 0.78 Directed Unipartite title cited 5 KiB 7 KiB 6 KiB 6 KiB
citations_T107 111 149 1.34 1.95 3.78 8.97 0.02 0.12 6 0.14 Directed Unipartite title cited 6 KiB 8 KiB 8 KiB 7 KiB
citations_T131 86 97 1.13 2.00 1.81 23.52 -0.33 0.04 6 0.28 Directed Unipartite title cited 6 KiB 7 KiB 7 KiB 6 KiB
citations_T144 140 147 1.05 1.63 2.46 15.16 0.16 0.12 7 0.11 Directed Unipartite title cited 8 KiB 10 KiB 10 KiB 9 KiB
citations_T145 171 255 1.49 2.77 3.15 34.92 0.05 0.12 8 0.37 Directed Unipartite title cited 9 KiB 12 KiB 11 KiB 10 KiB
citations_T162 146 261 1.79 2.68 2.35 77.97 0.01 0.12 12 0.25 Directed Unipartite title cited 8 KiB 11 KiB 10 KiB 9 KiB
citations_T182 153 225 1.47 2.38 1.78 10.34 -0.10 0.11 6 0.12 Directed Unipartite title cited 9 KiB 11 KiB 11 KiB 9 KiB
citations_T199 109 228 2.09 2.75 1.94 38.17 -0.06 0.07 12 0.63 Directed Unipartite title cited 7 KiB 8 KiB 8 KiB 7 KiB
citations_all 2,555 6,101 2.39 5.65 13.45 272.14 0.11 0.18 15 0.61 Directed Unipartite title year venue authors 141 KiB 173 KiB 171 KiB 172 KiB
movies 34,283 142,427 8.31 18.98 37.05 91.65 -0.02 0.04 13 0.78 Undirected Unipartite name words type categories 1.7 MiB 2.2 MiB 2.2 MiB 2.6 MiB
Ridiculograms*
* These are automatically generated force-directed visualizations, and can be quite meaningless for networks both big and small. They should not be taken seriously as sources of scientific insight. See here for a discussion.