Link analysis for Web spam detection

Abstract

We propose link-based techniques for automating the detection of Web spam, a term referring to pages which use deceptive techniques to obtain undeservedly high scores in search engines. The issue of Web spam is widespread and difficult to solve, mostly due to the large size of the Web which means that, in practice, many algorithms are infeasible.We perform a statistical analysis of a large collection of Web pages. In particular, we compute statistics of the links in the vicinity of every Web page applying rank propagation and probabilistic counting over the entire Web graph in a scalable way. We build several automatic web spam classifiers using different techniques. This paper presents a study of the performance of each of these classifiers alone, as well as their combined performance.Based on these results we propose spam detection techniques which only consider the link structure of Web, regardless of page contents. These statistical features are used to build a classifier that is tested over a large collection of Web link spam. After ten-fold cross-validation, our best classifiers have a performance comparable to that of state-of-the-art spam classifiers that use content attributes, and orthogonal to their methods.

Understanding and combating link farming in the twitter social network

“…In comparison, research on Web spam has reached the 'next' stage beyond basic spam detection, such as understanding how spammers are actually establishing links in the Web in order to deceive searchengines [5] and unearthing the support structures (such as specific ISPs) for Web spammers [22]. Our study takes the first important step to reach a similar 'next' level in the study of Twitter spam, by unveiling the 'support structures' for spammers in Twitter.…”

“…Link-based statistics were used by Becchetti et al [5] to build a classifier for automatic detection of Web-spam. Gyongyi et al proposed the Trustrank algorithm [15] to combat web spam, where the basic assumption is that good pages usually link to other good pages; hence they start by assigning high scores to a set of known good pages, and then propagate the good ranks in a way similar to Pagerank.…”

Approximate Counting with a Floating-Point Counter

“…Memory may become a limiting factor even on mainstream desktop computers in demanding applications such as Webgraph analyses [3,4]. Numerous bioinformatics studies also require space-efficient solutions when searching for recurrent motifs in protein and DNA sequences.…”

Tendencias en minería de datos de la Web

“…El análisis de spam incluye resultados sólo basados en la estructura de la web (spam de enlaces 7,9 ) o en el contenido del texto (spam de contenido).…”