I found "Mining the web - discovering knowledge from Hypertext Data" by Soumen Ckakrabarti a usefull reference.
http://www.amazon.com/gp/product/1558607544/103-9548474-1631829?v=glance&n=283155 Rgrds, Thomas On 8/29/06, Andrzej Bialecki <[EMAIL PROTECTED]> wrote:
Mladen Adamovic wrote: > Hi! > > I want to get more insight into various search engine algorithms. I > have wide knowledge of standard data structures & algorithms > (hashvalues, trees, graphs, etc.). I thought that Lucene would be > good place to start to seek for information and indeed I've found some > decent information at Nutch website. However, I decided to post here > some personal opinions regarding this issue thinking that someone > might give me even more information. > > As far as I understand I should read books about Informational > Retrieval (i.e. Modern Information Retrieval by Balza-Yates, > Ribero-Neto). Any update? > > I also found using one article about link spam and citeseer wide > articles about link spam techniques, namely: > 1. Undue Influence: Eliminating the Impact of Link Plagiarism on Web > Search Rankings > 2. Using Rank Propagation and Probabilistic Counting for LinkBased > Spam Detection > 3. SpamRank Fully Automatic Link Spam Detection > 4. Identifying Link Farm Spam Pages > 5. Thwarting the Nigritude Ultramarine: Learning to Identify Link Spam Yes, good references. At this moment most of my working knowledge about search engines comes either from the book you cited above, or from papers found on Citeseer - play around with IR related terms, you will find a LOT of papers to read... ;). And then follow references from those papers ... I also found that other printed books are either too outdated or not so relevant to web-scale IR. In the end (as usually) the best way to really dig into the subject is to try and solve a real-life problem, combining the tools you already have and what you have learned. -- Best regards, Andrzej Bialecki <>< ___. ___ ___ ___ _ _ __________________________________ [__ || __|__/|__||\/| Information Retrieval, Semantic Web ___|||__|| \| || | Embedded Unix, System Integration http://www.sigram.com Contact: info at sigram dot com
