History of twitter_2009

The changes to the source code of this entry in the repository, newest first, each with the differences it made to the entry's files. They are also listed on GitLab.

2026-10-25 [entries] Fix parse bugs and improve descriptions and metadata by Tiago de Paula Peixoto 6bb6851

- parse fixes from the review of the descriptions, e.g. us_patents
  (directed), celegans_2019 (synapse direction), ecoli_transcription and
  yeast_transcription (regulator to target), bitcoin (direction, phantom
  node), ego_social (Google+ features and circles), scotus_majority,
  arxiv_authors and social_location (as in SNAP), caida_as, dnc, dom,
  mist, reuters and bibsonomy (names on the right nodes), uci_zoo
- every description now states explicitly what the nodes and edges
  represent; corrected titles, years, tags, citations and licences
- the "Hypergraph" tag is removed; very large entries are marked
  `huge = True` (see --skip-huge)
- ICON ids of partial duplicates added (hiv_transmission, congress_bills,
  openflights, dutch_school)

diff --git a/entries/twitter_2009/__init__.py b/entries/twitter_2009/__init__.py
index 9c354ad..eea33e0 100644
--- a/entries/twitter_2009/__init__.py
+++ b/entries/twitter_2009/__init__.py
@@ -19,13 +19,18 @@
 from .. import *
 
 title = "Twitter graph (2009)"
-description = """A large (possibly complete) snapshot of Twitter in 2009, represented as an anonymized network of accounts and their follow links.[^icon]
-[^icon]: Description obtained from the [ICON](https://icon.colorado.edu) project."""
+description = r"""Directed network of follow relationships among Twitter users, based on a crawl of the whole Twitter network performed by M. Cha, H. Haddadi, F. Benevenuto and K. P. Gummadi (Max Planck Institute for Software Systems), which aimed at collecting all users and links of Twitter at the time; the distributed data correspond to the snapshot of September 2009. Nodes are users, with anonymized identifiers, and an edge $i \to j$ indicates that user $i$ follows user $j$. The network has about 52.6 million nodes (the users that have at least one link) and 1,963,263,821 edges.
+
+The network has the following properties:
+
+- `name`: the anonymized user identifier."""
 tags = ['Social', 'Online', 'Unweighted']
 url = 'http://twitter.mpi-sws.org/'
-citation = [('M. Cha, H. Haddadi, F. Benevenuto, and K. P. Gummadi, "Measuring User Influence in Twitter: The Million Follower Fallacy" Proc. Internat. AAAI Conf. on Weblogs and Social Media (ICWSM), 10-17 (2010).', 'https://doi.org/10.1145/2897659.2897663')]
+citation = [('M. Cha, H. Haddadi, F. Benevenuto, and K. P. Gummadi, "Measuring User Influence in Twitter: The Million Follower Fallacy" Proc. Internat. AAAI Conf. on Weblogs and Social Media (ICWSM), 10-17 (2010).', 'https://doi.org/10.1609/icwsm.v4i1.14033')]
 icon_hash = '56a85c8e26855e083a2f78d4'
-ustream_license = None
+upstream_license = None
+# Too large to process on an ordinary machine (see --skip-huge)
+huge = True
 upstream_prefix = 'http://twitter.mpi-sws.org/'
 files = [('links-anon.txt.gz', None, None)]

2026-10-24 Update copyright information by Tiago de Paula Peixoto 73a4f0d

diff --git a/entries/twitter_2009/__init__.py b/entries/twitter_2009/__init__.py
index 247ed11..9c354ad 100644
--- a/entries/twitter_2009/__init__.py
+++ b/entries/twitter_2009/__init__.py
@@ -1,7 +1,7 @@
 #! /usr/bin/env python
 # -*- coding: utf-8 -*-
 #
-# Copyright (C) 2020-2024 Tiago de Paula Peixoto <tiago@skewed.de>
+# Copyright (C) 2020-2026 Tiago de Paula Peixoto <tiago@skewed.de>
 #
 # This program is free software: you can redistribute it and/or modify it under
 # the terms of the GNU Affero General Public License as published by the Free

2024-05-27 Update copyright information by Tiago de Paula Peixoto 3d288ea

diff --git a/entries/twitter_2009/__init__.py b/entries/twitter_2009/__init__.py
index 14a9574..247ed11 100644
--- a/entries/twitter_2009/__init__.py
+++ b/entries/twitter_2009/__init__.py
@@ -1,7 +1,7 @@
 #! /usr/bin/env python
 # -*- coding: utf-8 -*-
 #
-# Copyright (C) 2020-2023 Tiago de Paula Peixoto <tiago@skewed.de>
+# Copyright (C) 2020-2024 Tiago de Paula Peixoto <tiago@skewed.de>
 #
 # This program is free software: you can redistribute it and/or modify it under
 # the terms of the GNU Affero General Public License as published by the Free

2023-02-19 Update copyright information by Tiago de Paula Peixoto 8d005ae

diff --git a/entries/twitter_2009/__init__.py b/entries/twitter_2009/__init__.py
index 75452b6..14a9574 100644
--- a/entries/twitter_2009/__init__.py
+++ b/entries/twitter_2009/__init__.py
@@ -1,7 +1,7 @@
 #! /usr/bin/env python
 # -*- coding: utf-8 -*-
 #
-# Copyright (C) 2021 Tiago de Paula Peixoto <tiago@skewed.de>
+# Copyright (C) 2020-2023 Tiago de Paula Peixoto <tiago@skewed.de>
 #
 # This program is free software: you can redistribute it and/or modify it under
 # the terms of the GNU Affero General Public License as published by the Free

2021-06-22 Update copyright info by Tiago de Paula Peixoto db2efcc

diff --git a/entries/twitter_2009/__init__.py b/entries/twitter_2009/__init__.py
index ee96820..75452b6 100644
--- a/entries/twitter_2009/__init__.py
+++ b/entries/twitter_2009/__init__.py
@@ -1,7 +1,7 @@
 #! /usr/bin/env python
 # -*- coding: utf-8 -*-
 #
-# Copyright (C) 2020 Tiago de Paula Peixoto <tiago@skewed.de>
+# Copyright (C) 2021 Tiago de Paula Peixoto <tiago@skewed.de>
 #
 # This program is free software: you can redistribute it and/or modify it under
 # the terms of the GNU Affero General Public License as published by the Free

2020-11-28 Update citations to use DOIs by Tiago de Paula Peixoto e878874

diff --git a/entries/twitter_2009/__init__.py b/entries/twitter_2009/__init__.py
index 0de776b..ee96820 100644
--- a/entries/twitter_2009/__init__.py
+++ b/entries/twitter_2009/__init__.py
@@ -23,7 +23,7 @@ description = """A large (possibly complete) snapshot of Twitter in 2009, repres
 [^icon]: Description obtained from the [ICON](https://icon.colorado.edu) project."""
 tags = ['Social', 'Online', 'Unweighted']
 url = 'http://twitter.mpi-sws.org/'
-citation = [('M. Cha, H. Haddadi, F. Benevenuto, and K. P. Gummadi, "Measuring User Influence in Twitter: The Million Follower Fallacy" Proc. Internat. AAAI Conf. on Weblogs and Social Media (ICWSM), 10-17 (2010).', 'http://twitter.mpi-sws.org/icwsm2010_fallacy.pdf')]
+citation = [('M. Cha, H. Haddadi, F. Benevenuto, and K. P. Gummadi, "Measuring User Influence in Twitter: The Million Follower Fallacy" Proc. Internat. AAAI Conf. on Weblogs and Social Media (ICWSM), 10-17 (2010).', 'https://doi.org/10.1145/2897659.2897663')]
 icon_hash = '56a85c8e26855e083a2f78d4'
 ustream_license = None
 upstream_prefix = 'http://twitter.mpi-sws.org/'

2020-09-26 Add twitter_2009 by Tiago de Paula Peixoto a2ba210

diff --git a/entries/twitter_2009/__init__.py b/entries/twitter_2009/__init__.py
new file mode 100644
index 0000000..0de776b
--- /dev/null
+++ b/entries/twitter_2009/__init__.py
@@ -0,0 +1,55 @@
+#! /usr/bin/env python
+# -*- coding: utf-8 -*-
+#
+# Copyright (C) 2020 Tiago de Paula Peixoto <tiago@skewed.de>
+#
+# This program is free software: you can redistribute it and/or modify it under
+# the terms of the GNU Affero General Public License as published by the Free
+# Software Foundation, either version 3 of the License, or (at your option) any
+# later version.
+#
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+# FOR A PARTICULAR PURPOSE.  See the GNU Affero General Public License for more
+# details.
+#
+# You should have received a copy of the GNU Affero General Public License along
+# with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+from .. import *
+
+title = "Twitter graph (2009)"
+description = """A large (possibly complete) snapshot of Twitter in 2009, represented as an anonymized network of accounts and their follow links.[^icon]
+[^icon]: Description obtained from the [ICON](https://icon.colorado.edu) project."""
+tags = ['Social', 'Online', 'Unweighted']
+url = 'http://twitter.mpi-sws.org/'
+citation = [('M. Cha, H. Haddadi, F. Benevenuto, and K. P. Gummadi, "Measuring User Influence in Twitter: The Million Follower Fallacy" Proc. Internat. AAAI Conf. on Weblogs and Social Media (ICWSM), 10-17 (2010).', 'http://twitter.mpi-sws.org/icwsm2010_fallacy.pdf')]
+icon_hash = '56a85c8e26855e083a2f78d4'
+ustream_license = None
+upstream_prefix = 'http://twitter.mpi-sws.org/'
+files = [('links-anon.txt.gz', None, None)]
+
+def fetch_upstream(force=False):
+    return fetch_upstream_files(__name__.split(".")[-1], upstream_prefix, files,
+                                force)
+
+@cache_network()
+@coerce_props()
+@annotate()
+def parse(alts=None):
+    global files
+    name = __name__.split(".")[-1]
+    for fnames, alt, fmt in files:
+        if alts is not None and alt not in alts:
+            continue
+        if isinstance(fnames, str):
+            fnames = [fnames]
+        with ExitStack() as stack:
+            fs = [stack.enter_context(open_upstream_file(name, fn, "r")) for fn in fnames]
+            def edges():
+                for line in fs[0]:
+                    vs = line.split()
+                    yield int(vs[0]), int(vs[1])
+            g = Graph()
+            g.vp.name = g.add_edge_list(edges(), hashed=True, hash_type="int")
+        yield alt, g