C. Huang, Q. Jiang, and Y. Zhang. Proceedings of the 2010 international conference on Web-age information management, page 222--233. Berlin, Heidelberg, Springer-Verlag, (2010)
Abstract
In theWeb 2.0 eras, the individual Internet users can also act as information providers, releasing information or making comments conveniently. However, some participants may spread irresponsible remarks or express irrelevant comments for commercial interests. This kind of so-called comment spam severely hurts the information quality. This paper tries to automatically detect comment spam through content analysis, using some previously-undescribed features. Experiments on a real data set show that our combined heuristics can correctly identify comment spam with high precision(90.4%) and recall(84.5%).
%0 Conference Paper
%1 Huang2010a
%A Huang, Congrui
%A Jiang, Qiancheng
%A Zhang, Yan
%B Proceedings of the 2010 international conference on Web-age information management
%C Berlin, Heidelberg
%D 2010
%I Springer-Verlag
%K web-2.0 spam-detection content-analysis comment
%P 222--233
%T Detecting comment spam through content analysis
%U http://portal.acm.org/citation.cfm?id=1927585.1927611
%X In theWeb 2.0 eras, the individual Internet users can also act as information providers, releasing information or making comments conveniently. However, some participants may spread irresponsible remarks or express irrelevant comments for commercial interests. This kind of so-called comment spam severely hurts the information quality. This paper tries to automatically detect comment spam through content analysis, using some previously-undescribed features. Experiments on a real data set show that our combined heuristics can correctly identify comment spam with high precision(90.4%) and recall(84.5%).
%@ 3-642-16719-5, 978-3-642-16719-5
@inproceedings{Huang2010a,
abstract = {In theWeb 2.0 eras, the individual Internet users can also act as information providers, releasing information or making comments conveniently. However, some participants may spread irresponsible remarks or express irrelevant comments for commercial interests. This kind of so-called comment spam severely hurts the information quality. This paper tries to automatically detect comment spam through content analysis, using some previously-undescribed features. Experiments on a real data set show that our combined heuristics can correctly identify comment spam with high precision(90.4%) and recall(84.5%).},
acmid = {1927611},
added-at = {2011-03-17T13:22:55.000+0100},
address = {Berlin, Heidelberg},
author = {Huang, Congrui and Jiang, Qiancheng and Zhang, Yan},
biburl = {https://www.bibsonomy.org/bibtex/24b0ad26ece5e6e1f110976fcb2bf6514/beate},
booktitle = {Proceedings of the 2010 international conference on Web-age information management},
description = {Detecting comment spam through content analysis},
groups = {public},
interhash = {e780b5d4471f8ea5dd12f41652e63f3e},
intrahash = {4b0ad26ece5e6e1f110976fcb2bf6514},
isbn = {3-642-16719-5, 978-3-642-16719-5},
keywords = {web-2.0 spam-detection content-analysis comment},
location = {Jiuzhaigou Valley, China},
numpages = {12},
pages = {222--233},
publisher = {Springer-Verlag},
series = {WAIM'10},
timestamp = {2011-03-25T15:29:34.000+0100},
title = {Detecting comment spam through content analysis},
url = {http://portal.acm.org/citation.cfm?id=1927585.1927611},
username = {beate},
year = 2010
}