Focused crawling: a new approach to topic-specific Web resource discovery Export

@article{citeulike:276823, abstract = {The rapid growth of the World-Wide Web poses unprecedented scaling challenges for general-purpose crawlers and search engines. In this paper we describe a new hypertext resource discovery system called a Focused Crawler. The goal of a focused crawler is to selectively seek out pages that are relevant to a pre-defined set of topics. The topics are specified not using keywords, but using exemplary documents. Rather than collecting and indexing all accessible Web documents to be able to answer all ...}, author = {Chakrabarti, Soumen and van den Berg, Martin and Dom, Byron}, citeulike-article-id = {276823}, citeulike-linkout-0 = {http://citeseer.ist.psu.edu/chakrabarti99focused.html}, citeulike-linkout-1 = {http://citeseer.lcs.mit.edu/chakrabarti99focused.html}, citeulike-linkout-2 = {http://citeseer.ifi.unizh.ch/chakrabarti99focused.html}, citeulike-linkout-3 = {http://citeseer.comp.nus.edu.sg/chakrabarti99focused.html}, journal = {Computer Networks (Amsterdam, Netherlands: 1999)}, keywords = {crawler, focused\_crawling, ibm, iit}, number = {11--16}, pages = {1623--1640}, posted-at = {2007-10-13 17:44:27}, priority = {3}, title = {Focused crawling: a new approach to topic-specific Web resource discovery}, url = {http://citeseer.ist.psu.edu/chakrabarti99focused.html}, volume = {31}, year = {1999} }

TY - JOUR ID - citeulike:276823 L3 - citeulike-article-id:276823 N2 - The rapid growth of the World-Wide Web poses unprecedented scaling challenges for general-purpose crawlers and search engines. In this paper we describe a new hypertext resource discovery system called a Focused Crawler. The goal of a focused crawler is to selectively seek out pages that are relevant to a pre-defined set of topics. The topics are specified not using keywords, but using exemplary documents. Rather than collecting and indexing all accessible Web documents to be able to answer all ... IS - 11--16 JF - Computer Networks (Amsterdam, Netherlands: 1999) EP - 1640 TI - Focused crawling: a new approach to topic-specific Web resource discovery VL - 31 SP - 1623 KW - crawler KW - focused_crawling KW - ibm KW - iit AU - Chakrabarti, Soumen AU - van den Berg, Martin AU - Dom, Byron PY - 1999/// UR - http://citeseer.ist.psu.edu/chakrabarti99focused.html ER -