期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2018
卷号：6
期号：4
页码：3436-3445
DOI：10.15680/IJIRCCE.2018.0604040
出版社：S&S Publications
摘要：Today,a lot of people depend onavailablecontent in online networking in their choices (e.g. surveys and
criticism on a subject or item). The likelihood that anyone can leave a survey give a brilliant chance to spammers to
compose spam audits about items and administrations for various interests. Recognizing these spammers and the spam
content is an intriguing issue of research and in spite of the fact that an extensive number of studies have been done as
of late toward this end, yet so far the procedures set forth still scarcely distinguish spam surveys, and none of them
demonstrate the significance of each removed element compose. In this investigation,proposing a novel structure,
named NetSpam, which uses spam highlights for displaying survey datasets as heterogeneous data systems to outline
discovery methodology into a classification issue in such systems. Utilizing the significance of spam highlights help us
to get better outcomes as far as various measurements probed true survey datasets from Yelp and Amazon sites. The
outcomes demonstrate that NetSpam beats the current techniques and among four classes of highlights;including
review- behavioral, user-behavioral, review-linguistic,user-linguistic, thefirsttypeoffeaturesperformsbetter than
alternate classifications.
