Boosting the Performance of Web Spam Detection with Ensemble Under-Sampling Classification

Geng, Guanggang; Wang, Chunheng; Li, Qiu-Dan; Xu, Lei; Jin, Xiao-Bo

doi:10.1109/fskd.2007.207

Cited by 41 publications

(21 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Considering the web spam domain from a machine learning perspective, we analysed the behaviour of two wellknown state-of-the-art algorithms for web spam classification (i.e., SVM and C5.0) comparing their performance first as individual classifiers and then as hybridized classifiers (using regular expressions) in our WSF2 framework. These classifiers were selected because of their effectiveness and relative efficiency as evidenced in previous research works [17,23,38,39]. Although regular expressions used as an individual technique achieve poor results in spam filtering, their proper combination with other machine learning approaches improves the accuracy of definitive antispam classification.…”

Section: Case Studymentioning

confidence: 99%

See 1 more Smart Citation

WSF2: A Novel Framework for Filtering Web Spam

Fdez-Glez

Ruano-Ordás

Laza

et al. 2016

Scientific Programming

View full text Add to dashboard Cite

Over the last years, research on web spam filtering has gained interest from both academia and industry. In this context, although there are a good number of successful antispam techniques available (i.e., content-based, link-based, and hiding), an adequate combination of different algorithms supported by an advanced web spam filtering platform would offer more promising results. To this end, we propose the WSF2 framework, a new platform particularly suitable for filtering spam content on web pages. Currently, our framework allows the easy combination of different filtering techniques including, but not limited to, regular expressions and well-known classifiers (i.e., Naïve Bayes, Support Vector Machines, and C5.0). Applying our WSF2 framework over the publicly available WEBSPAM-UK2007 corpus, we have been able to demonstrate that a simple combination of different techniques is able to improve the accuracy of single classifiers on web spam detection. As a result, we conclude that the proposed filtering platform is a powerful tool for boosting applied research in this area.

show abstract

Section: Case Studymentioning

confidence: 99%

“…In fact, Geng and colleagues [23] introduced the first proposal using both content-and link-based features to detect web spam pages. In the same line, the work of Becchetti and colleagues [24] combined link-and contentbased features using C4.5 to detect web spam.…”

Section: Related Work On Web Spam Filteringmentioning

confidence: 99%

WSF2: A Novel Framework for Filtering Web Spam

Fdez-Glez

Ruano-Ordás

Laza

et al. 2016

Scientific Programming

View full text Add to dashboard Cite

show abstract

“…can be used as classification algorithms on imbalance datasets. Geng et al proposed a novel ensemble classifier based on under-sampling technique and C4.5 decision tree classifier for web spam detection and achieved good results [12].…”

Section: B Solving Class Imbalance Problem On Web Spam Datasetmentioning

confidence: 99%

“…examples in N-N', is neglected, and the neglect leads to the main deficiency of under-sampling algorithm. An ensemble strategy can be used to overcome the deficiency and keep the efficiency of under-sampling [12]- [14]. Different from [12]- [14], we set the number of N' approximately equal to the number of S, and divide all of the N samples into several N' samples subset randomly.…”

Section: A Ensemble Based On Under-samplingmentioning

confidence: 99%

“…An ensemble strategy can be used to overcome the deficiency and keep the efficiency of under-sampling [12]- [14]. Different from [12]- [14], we set the number of N' approximately equal to the number of S, and divide all of the N samples into several N' samples subset randomly. As result, the sampling ratio K = N'/N and M=N/N' sub datasets are obtained.…”

Section: A Ensemble Based On Under-samplingmentioning

confidence: 99%

See 1 more Smart Citation