We describe the techniques developed to gather and distribute in a highly compressed, yet accessible, form a series of twelve snapshot of the .uk web domain. Ad hoc compression techniques made it possible to store the twelve snapshots using just 1:9 bits per link, with constant-time access to temporal information. Our collection makes it possible to study the temporal evolution link-based scores (e.g., PageRank), the growth of online communities, and in general time-dependent phenomena related to the link structure.
%0 Journal Article
%1 boldi2008large
%A Boldi, Paolo
%A Santini, Massimo
%A Vigna, Sebastiano
%C New York, NY, USA
%D 2008
%I ACM
%J SIGIR Forum
%K archive gaw graph pulse web
%N 2
%P 33--38
%R 10.1145/1480506.1480511
%T A Large Time-aware Web Graph
%U http://doi.acm.org/10.1145/1480506.1480511
%V 42
%X We describe the techniques developed to gather and distribute in a highly compressed, yet accessible, form a series of twelve snapshot of the .uk web domain. Ad hoc compression techniques made it possible to store the twelve snapshots using just 1:9 bits per link, with constant-time access to temporal information. Our collection makes it possible to study the temporal evolution link-based scores (e.g., PageRank), the growth of online communities, and in general time-dependent phenomena related to the link structure.
@article{boldi2008large,
abstract = {We describe the techniques developed to gather and distribute in a highly compressed, yet accessible, form a series of twelve snapshot of the .uk web domain. Ad hoc compression techniques made it possible to store the twelve snapshots using just 1:9 bits per link, with constant-time access to temporal information. Our collection makes it possible to study the temporal evolution link-based scores (e.g., PageRank), the growth of online communities, and in general time-dependent phenomena related to the link structure.},
acmid = {1480511},
added-at = {2017-06-12T12:37:38.000+0200},
address = {New York, NY, USA},
author = {Boldi, Paolo and Santini, Massimo and Vigna, Sebastiano},
biburl = {https://www.bibsonomy.org/bibtex/2a22e5b42dc6b28c291c668088e73fbe7/jaeschke},
description = {A large time-aware web graph},
doi = {10.1145/1480506.1480511},
interhash = {c0febc0fd52822485278238e70122b7f},
intrahash = {a22e5b42dc6b28c291c668088e73fbe7},
issn = {0163-5840},
issue_date = {December 2008},
journal = {SIGIR Forum},
keywords = {archive gaw graph pulse web},
month = nov,
number = 2,
numpages = {6},
pages = {33--38},
publisher = {ACM},
timestamp = {2017-06-12T12:37:38.000+0200},
title = {A Large Time-aware Web Graph},
url = {http://doi.acm.org/10.1145/1480506.1480511},
volume = 42,
year = 2008
}