threads-stack-overflow dataset
This is a temporal higher-order network dataset, which here means a
sequence of timestamped simplices where each simplex is a set of
nodes. In this dataset, nodes are users
on stackoverflow.com, and a
simplex comes from users participating in a thread that lasts for at
most 24 hours. The timestamps are the time of the post in
millisecond but normalized so that the earliest post starts at 0.
The projected graph is a weighted undirected graph representing how
many times each pair of nodes co-appears in a simplex. We restricted
to simplices that consist of at most 25 nodes. Some basic statistics
of this dataset are:
- number of nodes: 2,675,955
- number of timestamped simplices: 11,305,343
- number of unique simplices: 9,705,709
- number of edges in projected graph: 20,999,838
- threads-stack-overflow.tar.gz (timestamped simplices and simplex labels)
- threads-stack-overflow-proj-graph.tar.gz (weighted projected graph)
- threads-stack-overflow-full.tar.gz (timestamped simplices and simplex labels)
- threads-stack-overflow-full-proj-graph.tar.gz (weighted projected graph)
- Simplicial closure and higher-order link prediction.
Austin R. Benson, Rediet Abebe, Michael T. Schaub, Ali Jadbabaie, and Jon Kleinberg.
Proceedings of the National Academy of Sciences (PNAS), 2018. [bibtex]