Transductive Link Spam Detection

Web spam can significantly deteriorate the quality of search engines. Early web spamming techniques mainly manipulate page content. Since linkage information is widely used in web search, link-based spamming has also developed. So far, many techniques have been proposed to detect link spam. Those approaches are basically variants of link-based web ranking methods. In contrast, we cast the link spam detection problem into a machine learning problem of classification on directed graphs. We develop discrete analysis on directed graphs, and construct a discrete analogue of classical regularization theory via discrete analysis. A classification algorithm for directed graphs is then derived from the discrete regularization. We have applied the approach to real-world link spam detection problems, and encouraging results have been obtained. Categories and Subject Descriptors H.3.3 [Information Search and Retrieval]: Retrieval models; I.2.6 [Learning]: Concept learning; G.2.2 [Graph Theory]...

• Type: Conference
• Year: 2007
• Where: AIRWEB
• Authors: Dengyong Zhou, Chris Burges, Tao Tao
• Keywords: AIRWEB 2007, Directed Graph, Discrete Analysis, Internet Technology, Link Spam