Social bookmarking is a recent phenomenon which has the
potential to give us a great deal of data about pages on the
web. One major question is whether that data can be used
to augment systems like web search. To answer this question,
over the past year we have gathered what we believe
to be the largest dataset from a social bookmarking site yet
analyzed by academic researchers. Our dataset represents
about forty million bookmarks from the social bookmarking
site del.icio.us. We contribute a characterization of posts to
del.icio.us: how many bookmarks exist (about 115 million),
how fast is it growing, and how active are the URLs being
posted about (quite active). We also contribute a characterization
of tags used by bookmarkers. We found that certain
tags tend to gravitate towards certain domains, and vice
versa. We also found that tags occur in over 50 percent
of the pages that they annotate, and in only 20 percent of
cases do they not occur in the page text, backlink page text,
or forward link page text of the pages they annotate. We
conclude that social bookmarking can provide search data
not currently provided by other sources, though it may currently
lack the size and distribution of tags necessary to
make a significant impact.
%0 Conference Paper
%1 paper:heymann:2007
%A Yanbe, Yusuke
%A Jatowt, Adam
%A Nakamura, Satoshi
%A Tanaka, Katsumi
%B JCDL '07: Proceedings of the 7th ACM/IEEE-CS joint conference on Digital libraries
%C New York, NY, USA
%D 2007
%I ACM
%K 2007 bookmarking search search-engines social tags
%P 107--116
%R http://doi.acm.org/10.1145/1255175.1255198
%T Can social bookmarking enhance search in the web?
%U http://portal.acm.org/citation.cfm?doid=1255175.1255198
%X Social bookmarking is a recent phenomenon which has the
potential to give us a great deal of data about pages on the
web. One major question is whether that data can be used
to augment systems like web search. To answer this question,
over the past year we have gathered what we believe
to be the largest dataset from a social bookmarking site yet
analyzed by academic researchers. Our dataset represents
about forty million bookmarks from the social bookmarking
site del.icio.us. We contribute a characterization of posts to
del.icio.us: how many bookmarks exist (about 115 million),
how fast is it growing, and how active are the URLs being
posted about (quite active). We also contribute a characterization
of tags used by bookmarkers. We found that certain
tags tend to gravitate towards certain domains, and vice
versa. We also found that tags occur in over 50 percent
of the pages that they annotate, and in only 20 percent of
cases do they not occur in the page text, backlink page text,
or forward link page text of the pages they annotate. We
conclude that social bookmarking can provide search data
not currently provided by other sources, though it may currently
lack the size and distribution of tags necessary to
make a significant impact.
%@ 978-1-59593-644-8
@inproceedings{paper:heymann:2007,
abstract = {Social bookmarking is a recent phenomenon which has the
potential to give us a great deal of data about pages on the
web. One major question is whether that data can be used
to augment systems like web search. To answer this question,
over the past year we have gathered what we believe
to be the largest dataset from a social bookmarking site yet
analyzed by academic researchers. Our dataset represents
about forty million bookmarks from the social bookmarking
site del.icio.us. We contribute a characterization of posts to
del.icio.us: how many bookmarks exist (about 115 million),
how fast is it growing, and how active are the URLs being
posted about (quite active). We also contribute a characterization
of tags used by bookmarkers. We found that certain
tags tend to gravitate towards certain domains, and vice
versa. We also found that tags occur in over 50 percent
of the pages that they annotate, and in only 20 percent of
cases do they not occur in the page text, backlink page text,
or forward link page text of the pages they annotate. We
conclude that social bookmarking can provide search data
not currently provided by other sources, though it may currently
lack the size and distribution of tags necessary to
make a significant impact.},
added-at = {2008-09-09T14:57:37.000+0200},
address = {New York, NY, USA},
author = {Yanbe, Yusuke and Jatowt, Adam and Nakamura, Satoshi and Tanaka, Katsumi},
biburl = {https://www.bibsonomy.org/bibtex/2d896ae22bc7b52edefbfb9cdb373cf83/mschuber},
booktitle = {JCDL '07: Proceedings of the 7th ACM/IEEE-CS joint conference on Digital libraries},
description = {Can social bookmarking enhance search in the web?},
doi = {http://doi.acm.org/10.1145/1255175.1255198},
interhash = {13ebfc0942b5908890c3caaa7046fe50},
intrahash = {d896ae22bc7b52edefbfb9cdb373cf83},
isbn = {978-1-59593-644-8},
keywords = {2007 bookmarking search search-engines social tags},
location = {Vancouver, BC, Canada},
pages = {107--116},
publisher = {ACM},
timestamp = {2008-09-09T14:57:37.000+0200},
title = {Can social bookmarking enhance search in the web?},
url = {http://portal.acm.org/citation.cfm?doid=1255175.1255198},
year = 2007
}