The popularity of social bookmarking systems became attractive to spammers to disturb systems by posting illegal or inappropriate web content links that users do not wish to share. We present a study of automatic detection of spammers in a social tagging system. Several distinct features are extracted that address various properties of social spam, which provide sufficient information to discriminate legitimate against spammer users. So these features are used for various machine learning algorithms to classify, achieving over 99% accuracy in detecting spammers.
Beschreibung
Spam detection in social bookmarking websites - IEEE Conference Publication
%0 Conference Paper
%1 poorgholami2013detection
%A Poorgholami, M.
%A Jalali, M.
%A Rahati, S.
%A Asgari, T.
%B 2013 IEEE 4th International Conference on Software Engineering and Service Science
%D 2013
%K bookmarking detection social spam
%P 56-59
%R 10.1109/ICSESS.2013.6615254
%T Spam detection in social bookmarking websites
%U http://ieeexplore.ieee.org/document/6615254/
%X The popularity of social bookmarking systems became attractive to spammers to disturb systems by posting illegal or inappropriate web content links that users do not wish to share. We present a study of automatic detection of spammers in a social tagging system. Several distinct features are extracted that address various properties of social spam, which provide sufficient information to discriminate legitimate against spammer users. So these features are used for various machine learning algorithms to classify, achieving over 99% accuracy in detecting spammers.
@inproceedings{poorgholami2013detection,
abstract = {The popularity of social bookmarking systems became attractive to spammers to disturb systems by posting illegal or inappropriate web content links that users do not wish to share. We present a study of automatic detection of spammers in a social tagging system. Several distinct features are extracted that address various properties of social spam, which provide sufficient information to discriminate legitimate against spammer users. So these features are used for various machine learning algorithms to classify, achieving over 99% accuracy in detecting spammers.},
added-at = {2017-09-17T23:21:06.000+0200},
author = {Poorgholami, M. and Jalali, M. and Rahati, S. and Asgari, T.},
biburl = {https://www.bibsonomy.org/bibtex/20fcd3c178b5b6acb8a3c1d9d0474fc14/nosebrain},
booktitle = {2013 IEEE 4th International Conference on Software Engineering and Service Science},
description = {Spam detection in social bookmarking websites - IEEE Conference Publication},
doi = {10.1109/ICSESS.2013.6615254},
interhash = {9a06bc02f5a4b1257ea7c6298dddbd41},
intrahash = {0fcd3c178b5b6acb8a3c1d9d0474fc14},
issn = {2327-0586},
keywords = {bookmarking detection social spam},
month = may,
pages = {56-59},
timestamp = {2017-09-17T23:21:06.000+0200},
title = {Spam detection in social bookmarking websites},
url = {http://ieeexplore.ieee.org/document/6615254/},
year = 2013
}