stackexchange_threads — Stack Exchange question threads (2008-2017)

Description

Bipartite networks of users and the question threads they took part in, on three question-and-answer sites of the Stack Exchange network, assembled by A. R. Benson and collaborators from the Stack Exchange data dump (archive.org), covering the history of each site up to August 2017. Only the threads in which the question and all its answers were posted within 24 hours are included; each such thread is connected to the user who asked the question and to the users who answered it, and is timestamped with the time of the question.

ask_ubuntu: Ask Ubuntu (askubuntu.com), a site for questions about the Ubuntu operating system. Threads span December 2009 to August 2017.
math_sx: Mathematics Stack Exchange (math.stackexchange.com). Threads span July 2010 to August 2017.
stack_overflow: Stack Overflow (stackoverflow.com), a site for programming questions. Threads span August 2008 to August 2017.
stack_overflow_25: the version of stack_overflow distributed by the source restricted to the threads with at most 25 users, which leaves out 13 threads (with 26 to 67 users), and the users who took part only in those. Its file of question ids is empty; the question ids were taken from the full version, whose other threads are the same, in the same order.

The users are anonymous (they are identified only by an index of the source data). A user who both asked and answered a question is connected to its thread once.

The networks have the following properties:

is_thread: whether the node is a thread (otherwise a user).
Thread nodes: question_id, the post id of the question on its site (so that, e.g., question 1 of ask_ubuntu is https://askubuntu.com/questions/1); time, the time of the question, in Unix time (seconds since 1970-01-01 UTC). The source data give the times in milliseconds relative to the earliest question; they were converted to absolute times by matching the creation times of a sample of the questions, obtained from the Stack Exchange API (the conversion is accurate to about one second, but for a few questions, e.g. migrated from other sites, the times of the data differ from the creation times of the API by up to a few hours).

Tags

Social Online Collaboration Unweighted Timestamps Metadata

Citation

A. R. Benson, R. Abebe, M. T. Schaub, A. Jadbabaie, J. Kleinberg, "Simplicial closure and higher-order link prediction." Proceedings of the National Academy of Sciences 115(48), E11221-E11230 (2018) 10.1073/pnas.1800683115 Sci-Hub

Upstream URL OK

https://www.cs.cornell.edu/~arb/data/threads-ask-ubuntu/
https://www.cs.cornell.edu/~arb/data/threads-math-sx/
https://www.cs.cornell.edu/~arb/data/threads-stack-overflow/

Upstream license

Creative Commons Attribution-ShareAlike (CC BY-SA; version 3.0 or 4.0, depending on the date of each post), https://stackoverflow.com/help/licensing

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	$\left<k\right>$	$\sigma_k$	$\lambda_h$	$\tau$	$r$	$\oslash$	$S$	Kind	Mode	NPs	gt	GraphML	GML	csv
ask_ubuntu	318,549	346,537	2.18	13.07	18.13	130.46	-0.08	28	0.72	Undirected	Bipartite	is_thread question_id time	2.2 MiB	3.3 MiB	3.2 MiB	3.9 MiB
math_sx	896,237	1,610,393	3.59	41.36	44.93	71.79	-0.09	19	0.94	Undirected	Bipartite	is_thread question_id time	9.2 MiB	13.1 MiB	12.6 MiB	14.9 MiB
stack_overflow	13,981,325	25,578,226	3.66	34.25	45.99	413.29	-0.04	27	0.94	Undirected	Bipartite	is_thread question_id time	165.4 MiB	229.7 MiB	217.2 MiB	265.6 MiB
stack_overflow_25	13,981,298	25,577,823	3.66	34.25	45.99	413.25	-0.04	27	0.94	Undirected	Bipartite	is_thread question_id time	165.3 MiB	229.7 MiB	217.0 MiB	265.6 MiB