{"id":"https://openalex.org/W2040869915","doi":"https://doi.org/10.1109/icdim.2011.6093329","title":"Automatic text classification and focused crawling","display_name":"Automatic text classification and focused crawling","publication_year":2011,"publication_date":"2011-09-01","ids":{"openalex":"https://openalex.org/W2040869915","doi":"https://doi.org/10.1109/icdim.2011.6093329","mag":"2040869915"},"language":"en","primary_location":{"id":"doi:10.1109/icdim.2011.6093329","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2011.6093329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 Sixth International Conference on Digital Information Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005167483","display_name":"Sameendra Samarawickrama","orcid":null},"institutions":[{"id":"https://openalex.org/I90678064","display_name":"University of Colombo","ror":"https://ror.org/02phn5242","country_code":"LK","type":"education","lineage":["https://openalex.org/I90678064"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Sameendra Samarawickrama","raw_affiliation_strings":["University of Colombo School of Computing, Colombo, Sri Lanka","University of Colombo School of Computing, 35, Reid Avenue, Colombo 7, Sri Lanka"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Colombo School of Computing, Colombo, Sri Lanka","institution_ids":["https://openalex.org/I90678064"]},{"raw_affiliation_string":"University of Colombo School of Computing, 35, Reid Avenue, Colombo 7, Sri Lanka","institution_ids":["https://openalex.org/I90678064"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087838047","display_name":"Lakshman Jayaratne","orcid":"https://orcid.org/0000-0002-0791-3334"},"institutions":[{"id":"https://openalex.org/I90678064","display_name":"University of Colombo","ror":"https://ror.org/02phn5242","country_code":"LK","type":"education","lineage":["https://openalex.org/I90678064"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Lakshman Jayaratne","raw_affiliation_strings":["University of Colombo School of Computing, Colombo, Sri Lanka","University of Colombo School of Computing, 35, Reid Avenue, Colombo 7, Sri Lanka"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Colombo School of Computing, Colombo, Sri Lanka","institution_ids":["https://openalex.org/I90678064"]},{"raw_affiliation_string":"University of Colombo School of Computing, 35, Reid Avenue, Colombo 7, Sri Lanka","institution_ids":["https://openalex.org/I90678064"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2924,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.90992707,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"2","issue":null,"first_page":"143","last_page":"148"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9319999814033508,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9300000071525574,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.9750585556030273},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.9315332770347595},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.809894323348999},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7414989471435547},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6881334781646729},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5893796682357788},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5685421228408813},{"id":"https://openalex.org/keywords/traverse","display_name":"Traverse","score":0.5249621272087097},{"id":"https://openalex.org/keywords/link-analysis","display_name":"Link analysis","score":0.5022695064544678},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4793011248111725},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.24548190832138062},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.18761011958122253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13552796840667725}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.9750585556030273},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.9315332770347595},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.809894323348999},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7414989471435547},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6881334781646729},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5893796682357788},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5685421228408813},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.5249621272087097},{"id":"https://openalex.org/C1173588","wikidata":"https://www.wikidata.org/wiki/Q6554294","display_name":"Link analysis","level":2,"score":0.5022695064544678},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4793011248111725},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.24548190832138062},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.18761011958122253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13552796840667725},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdim.2011.6093329","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2011.6093329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 Sixth International Conference on Digital Information Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W140650756","https://openalex.org/W173995639","https://openalex.org/W1548339651","https://openalex.org/W1571529277","https://openalex.org/W1573640501","https://openalex.org/W1580729871","https://openalex.org/W1963973829","https://openalex.org/W1999267468","https://openalex.org/W2001832505","https://openalex.org/W2014134732","https://openalex.org/W2017224880","https://openalex.org/W2071102467","https://openalex.org/W2087609354","https://openalex.org/W2099585315","https://openalex.org/W2107778970","https://openalex.org/W2118230419","https://openalex.org/W2119426258","https://openalex.org/W2123659440","https://openalex.org/W2171266073","https://openalex.org/W2461186194","https://openalex.org/W2971757778","https://openalex.org/W4285719527","https://openalex.org/W6605750074","https://openalex.org/W6632724502","https://openalex.org/W6634403407","https://openalex.org/W6634522407","https://openalex.org/W6719042568","https://openalex.org/W6767335072"],"related_works":["https://openalex.org/W4385695127","https://openalex.org/W2375180657","https://openalex.org/W4248730791","https://openalex.org/W2026132847","https://openalex.org/W1506122440","https://openalex.org/W2358310581","https://openalex.org/W2352686120","https://openalex.org/W2019080882","https://openalex.org/W2372594123","https://openalex.org/W2137810919"],"abstract_inverted_index":{"A":[0],"focused":[1,61,75,81,88],"crawler":[2,6],"is":[3,15,38],"a":[4,18,54],"web":[5,10,29,62],"that":[7,14],"traverse":[8],"the":[9,25,34,42,45,59,93,104,109],"to":[11,17,32,41,103],"explore":[12],"information":[13],"related":[16],"particular":[19],"topic":[20],"of":[21,47,56,58],"interest":[22],"only.":[23],"On":[24],"other":[26],"hand,":[27],"generic":[28],"crawlers":[30],"try":[31],"search":[33],"entire":[35],"web,":[36],"which":[37],"impossible":[39],"due":[40],"size":[43],"and":[44,87,95,107],"complexity":[46],"WWW.":[48],"In":[49],"this":[50],"paper":[51],"we":[52],"make":[53],"survey":[55],"some":[57],"latest":[60],"crawling":[63,76,82,89],"approaches":[64],"discussing":[65],"each":[66],"with":[67],"their":[68],"experimental":[69],"results.":[70],"We":[71,98],"categorize":[72],"them":[73],"as":[74],"based":[77,83,90],"on":[78,84,91],"content":[79,94],"analysis,":[80],"link":[85,96],"analysis":[86],"both":[92],"analysis.":[97],"also":[99],"give":[100],"an":[101],"insight":[102],"future":[105],"research":[106],"draw":[108],"overall":[110],"conclusions.":[111]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}