Multi-view web spam detection method

Abstract

The invention provides a multi-view web spam detection method. The method comprises the following steps of: firstly, obtaining two views of all normal pages and spam pages in the training data; then, two views of a page to be detected; respectively establishing a matrix for the obtained two views; resolving a normal norm and a spam norm; comparing the normal norm with the spam norm; if the normal norm is less than the spam norm, identifying the page to be detected as a normal page; if the normal norm is more than the spam norm, identifying the page to be detected as a spam page; if the normal norm is equal to the spam norm, randomly identifying the page to be detected as the normal page or the spam page. The method has the advantages of being insensitive to the unbalancedness of the training data, being capable of simultaneously detecting various spam pages, being simple in the detection process, and the like.

Description

technical field [0001] The invention relates to a multi-view network garbage page detection method, which belongs to the field of internet information retrieval. Background technique [0002] In order to obtain commercial benefits, some website owners use improper means to deceive the search engine website ranking algorithm, so that unimportant websites or pages are ranked higher, destroying the engine search results. Its related technologies include search engine optimization (SEO) and search engine marketing (SEM), which are collectively referred to as search engine spam, that is, Web spam (Internet spam). At present, Web spam has become an important challenge for various Web searches, seriously affecting the effect of information retrieval. At the same time, Web spam is developing rapidly, and new spamming technologies are constantly emerging. There are three main manifestations of Web spam: content-based, link (link) and page hiding. Currently, methods for detecting sp...

AI Technical Summary

Problems solved by technology

However, when the data dimension is large, there are the following problems: it is sensitive to the imbalance of training data, it cannot detect a variety of different spam pages at the same time, and the detection time complexity is high.

Studies have shown that once there is a large difference in the number of various types, especially for two types of problems, when the amount of one type of data is much larger than the amount of another type of data, the classifier obtained through learning will be more effective for the type with a small amount. (Minority class) classification accuracy will be greatly reduced

Images