With the increasing importance of search in guiding today’s web traffic, more and more effort has been spent to create search engine spam. Since link analysis is one of the most important factors in current commercial search engines’ ranking systems, new kinds of spam aiming at links have appeared. Building link farms is one technique that can deteriorate link-based ranking algorithms. In this paper, we present algorithms for detecting these link farms automatically by first generating a seed set based on the common link set between incoming and outgoing links of Web pages and then expanding it. Links between identified pages are re-weighted, providing a modified web graph to use in ranking page importance. Experimental results show that we can identify most link farm spam pages and the final ranking results are improved for almost all tested queries.
Link farm is a term which has been used in many papers, in this paper authors define it as and I am quoting here: “A network of web sites which are densely connected with each other”.
Main identifying method:
- Find domain name of incoming links of page X
- Find domain name of outgoing links of page X
- Find intersection between incoming and outgoing link
- If above intersection be greater than threshold, the mark page as bad page
- For each page which is not marked as bad in previous algorithm find all outgoing link
- For each outgoing link, if it link to a bad page which is more than threshold, then the page itself marked as a bad page.
- Do step 1 and 2 until there is not page marked whether or not as bad page.
- TKC effect
- In an study of Yahoo! search, about 68% of all queries have at least one spam page within the top 200 response list from the search engine. about 9% queries have at least one spam page within the top 10 list.
- R. Lempel and S. Moran. The stochastic approach fo link-structure analysis (SALSA) and the TKC eﬀect. Computer Networks, 33(1-6):387-401, 2000.