Distrust seed set propagation algorithm to detect web spam

作者：Goh Kwang Leng^*; Patchmuthu Ravi Kumar; Singh Ashutosh Kumar

来源：Journal of Intelligent Information Systems, 2017, 49(2): 213-235.

DOI：10.1007/s10844-016-0439-y

• Distrust propagation
• Link spamming
• Web spam

Web spam uses numerous techniques to misguide Web search engines in exchange of financial profit. A myriad of semi-automatic propagation model has been proposed with the purpose of combating Web spam. In this paper, distrust propagation is used to detect Web spam. An automatic distrust seed set propagation algorithm (DSP), which acts as an extension to the seed set to propagate distrust further to detect more Web spam. Experiments are conducted on WEBSPAM-UK2006 and WEBSPAM-UK2007 dataset; the results have shown that DSP enhanced the baseline algorithms and detected 17.73 % more spam hosts in the former dataset and detected 8.59 % more spam hosts in later dataset.

• 出版日期2017-10