{"id":"https://openalex.org/W2110034127","doi":"https://doi.org/10.1145/1242572.1242632","title":"An adaptive crawler for locating hidden-Web entry points","display_name":"An adaptive crawler for locating hidden-Web entry points","publication_year":2007,"publication_date":"2007-05-08","ids":{"openalex":"https://openalex.org/W2110034127","doi":"https://doi.org/10.1145/1242572.1242632","mag":"2110034127"},"language":"en","primary_location":{"id":"doi:10.1145/1242572.1242632","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1242572.1242632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th international conference on World Wide Web","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/A5000683692","display_name":"Luciano Barbosa","orcid":"https://orcid.org/0000-0002-6858-4773"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Luciano Barbosa","raw_affiliation_strings":["University of Utah, Salt Lake City, UT","University of Utah; Salt Lake City; UT"],"affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, UT","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"University of Utah; Salt Lake City; UT","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006773757","display_name":"Juliana Freire","orcid":"https://orcid.org/0000-0003-3915-7075"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juliana Freire","raw_affiliation_strings":["University of Utah, Salt Lake City, UT","University of Utah; Salt Lake City; UT"],"affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, UT","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"University of Utah; Salt Lake City; UT","institution_ids":["https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5000683692"],"corresponding_institution_ids":["https://openalex.org/I223532165"],"apc_list":null,"apc_paid":null,"fwci":24.8498,"has_fulltext":false,"cited_by_count":165,"citation_normalized_percentile":{"value":0.99358355,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"441","last_page":"450"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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/T11478","display_name":"Caching and Content Delivery","score":0.9843999743461609,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9613000154495239,"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/web-crawler","display_name":"Web crawler","score":0.9364819526672363},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.8903508186340332},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.8174804449081421},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7944208383560181},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.6350767612457275},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5981022119522095},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5140589475631714},{"id":"https://openalex.org/keywords/deep-web","display_name":"Deep Web","score":0.4406140446662903},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41680940985679626},{"id":"https://openalex.org/keywords/site-map","display_name":"Site map","score":0.41274234652519226},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.2937292456626892},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.18037763237953186},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.13455551862716675}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.9364819526672363},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8903508186340332},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.8174804449081421},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7944208383560181},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.6350767612457275},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5981022119522095},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5140589475631714},{"id":"https://openalex.org/C46721378","wikidata":"https://www.wikidata.org/wiki/Q221989","display_name":"Deep Web","level":3,"score":0.4406140446662903},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41680940985679626},{"id":"https://openalex.org/C67617509","wikidata":"https://www.wikidata.org/wiki/Q1503327","display_name":"Site map","level":5,"score":0.41274234652519226},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.2937292456626892},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.18037763237953186},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.13455551862716675},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1242572.1242632","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1242572.1242632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th international conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.113.8036","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.113.8036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utah.edu/~juliana/pub/ache-www2007.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.380.5495","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.380.5495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utah.edu/~lbarbosa/publications/ache.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W291262356","https://openalex.org/W1485536830","https://openalex.org/W1489992655","https://openalex.org/W1545169732","https://openalex.org/W1976232673","https://openalex.org/W2005579877","https://openalex.org/W2012426233","https://openalex.org/W2016892599","https://openalex.org/W2017726337","https://openalex.org/W2023450550","https://openalex.org/W2101302356","https://openalex.org/W2101610060","https://openalex.org/W2108489852","https://openalex.org/W2110780226","https://openalex.org/W2116780029","https://openalex.org/W2117058208","https://openalex.org/W2118356300","https://openalex.org/W2122410182","https://openalex.org/W2124673015","https://openalex.org/W2133034723","https://openalex.org/W2134007343","https://openalex.org/W2145102654","https://openalex.org/W2164896748","https://openalex.org/W2168661392","https://openalex.org/W2170188121","https://openalex.org/W2435251607","https://openalex.org/W2623293810","https://openalex.org/W2916858871","https://openalex.org/W3140730010","https://openalex.org/W6678087030","https://openalex.org/W6678701036","https://openalex.org/W6681291871","https://openalex.org/W6685116542","https://openalex.org/W6738852829"],"related_works":["https://openalex.org/W2375180657","https://openalex.org/W4385695127","https://openalex.org/W2026132847","https://openalex.org/W2137810919","https://openalex.org/W2358310581","https://openalex.org/W4248730791","https://openalex.org/W1506122440","https://openalex.org/W2384770049","https://openalex.org/W2364692302","https://openalex.org/W2371838993"],"abstract_inverted_index":{"In":[0],"this":[1,37],"paper":[2],"we":[3],"describe":[4],"new":[5,72],"adaptive":[6,120],"crawling":[7],"strategies":[8],"to":[9,15,44,66,124],"efficiently":[10],"locate":[11],"the":[12,27,41,46,55,85,91,119],"entry":[13],"points":[14],"hidden-Web":[16,21],"sources.":[17],"The":[18],"fact":[19],"that":[20,62,110],"sources":[22],"are":[23],"very":[24],"sparsely":[25],"distributedmakes":[26],"problem":[28,38],"of":[29,78,93,107],"locating":[30],"them":[31],"especially":[32],"challenging.":[33],"We":[34,69],"deal":[35],"with":[36],"by":[39,51,58],"using":[40],"contents":[42],"ofpages":[43],"focus":[45,83,135],"crawl":[47,86],"on":[48],"a":[49,71,105,133],"topic;":[50,56],"prioritizing":[52],"promisinglinks":[53,79],"within":[54],"and":[57,80],"also":[59],"following":[60],"links":[61],"may":[63],"not":[64],"lead":[65],"immediate":[67],"benefit.":[68],"propose":[70],"frameworkwhereby":[73],"crawlers":[74,121,131],"automatically":[75],"learn":[76],"patterns":[77],"adapt":[81],"their":[82],"as":[84,127,130],"progresses,":[87],"thus":[88],"greatly":[89],"reducing":[90],"amount":[92],"required":[94],"manual":[95],"setup":[96],"andtuning.":[97],"Our":[98],"experiments":[99],"over":[100],"real":[101],"Web":[102],"pages":[103],"in":[104,116],"representativeset":[106],"domains":[108],"indicate":[109],"online":[111],"learning":[112],"leadsto":[113],"significant":[114],"gains":[115],"harvest":[117],"rates'":[118],"retrieve":[122],"up":[123],"three":[125],"times":[126],"many":[128],"forms":[129],"thatuse":[132],"fixed":[134],"strategy.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":23},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":19},{"year":2012,"cited_by_count":18}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}