{"id":"https://openalex.org/W2081948558","doi":"https://doi.org/10.1145/1065385.1065407","title":"Downloading textual hidden web content through keyword queries","display_name":"Downloading textual hidden web content through keyword queries","publication_year":2005,"publication_date":"2005-06-07","ids":{"openalex":"https://openalex.org/W2081948558","doi":"https://doi.org/10.1145/1065385.1065407","mag":"2081948558"},"language":"en","primary_location":{"id":"doi:10.1145/1065385.1065407","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1065385.1065407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM/IEEE-CS joint conference on Digital libraries","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/A5030400740","display_name":"Alexandros Ntoulas","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]},{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799798094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexandros Ntoulas","raw_affiliation_strings":["UCLA","Dept. of Comput. Sci., California Univ., Los Angeles, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCLA","institution_ids":["https://openalex.org/I2799798094"]},{"raw_affiliation_string":"Dept. of Comput. Sci., California Univ., Los Angeles, CA#TAB#","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048986206","display_name":"Petros Zerfos","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]},{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799798094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Petros Zerfos","raw_affiliation_strings":["UCLA","Dept. of Comput. Sci., California Univ., Los Angeles, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCLA","institution_ids":["https://openalex.org/I2799798094"]},{"raw_affiliation_string":"Dept. of Comput. Sci., California Univ., Los Angeles, CA#TAB#","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073859348","display_name":"Junghoo Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]},{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799798094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junghoo Cho","raw_affiliation_strings":["UCLA","Dept. of Comput. Sci., California Univ., Los Angeles, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCLA","institution_ids":["https://openalex.org/I2799798094"]},{"raw_affiliation_string":"Dept. of Comput. Sci., California Univ., Los Angeles, CA#TAB#","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":36.4643,"has_fulltext":false,"cited_by_count":207,"citation_normalized_percentile":{"value":0.9964145,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"100","last_page":"109"},"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":0.991599977016449,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9639999866485596,"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/computer-science","display_name":"Computer science","score":0.8555850386619568},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.7143515944480896},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6865582466125488},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6220172643661499},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5923472046852112},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.5909779071807861},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.5801427364349365},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.4967377781867981},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.4887268543243408},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.46624913811683655},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.4521865248680115},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.4366956949234009},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.41671112179756165},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.4155682921409607},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.2469007670879364}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8555850386619568},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.7143515944480896},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6865582466125488},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6220172643661499},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5923472046852112},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.5909779071807861},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.5801427364349365},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.4967377781867981},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.4887268543243408},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.46624913811683655},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.4521865248680115},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.4366956949234009},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.41671112179756165},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.4155682921409607},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.2469007670879364}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1065385.1065407","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1065385.1065407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM/IEEE-CS joint conference on Digital libraries","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.105.137","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.105.137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ntoulas.net/pubs/ntoulas_hidden_web.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1570968730","https://openalex.org/W1586176254","https://openalex.org/W1605217017","https://openalex.org/W1969831559","https://openalex.org/W1986828474","https://openalex.org/W2027417216","https://openalex.org/W2039324760","https://openalex.org/W2072881690","https://openalex.org/W2078206416","https://openalex.org/W2079656678","https://openalex.org/W2096891167","https://openalex.org/W2108489852","https://openalex.org/W2109895155","https://openalex.org/W2118356300","https://openalex.org/W2125969310","https://openalex.org/W2131006463","https://openalex.org/W2137845970","https://openalex.org/W2147164982","https://openalex.org/W2151306141","https://openalex.org/W2152565070","https://openalex.org/W2152766222","https://openalex.org/W2157748587","https://openalex.org/W2169189540","https://openalex.org/W2170188121","https://openalex.org/W2221553715","https://openalex.org/W4247346926","https://openalex.org/W4250366158","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1994958611","https://openalex.org/W2402678663","https://openalex.org/W3199173531","https://openalex.org/W2277785728","https://openalex.org/W2379145789","https://openalex.org/W4200125296","https://openalex.org/W2945544759","https://openalex.org/W2610451498","https://openalex.org/W2109463504","https://openalex.org/W1547088227"],"abstract_inverted_index":{"An":[0],"ever-increasing":[1],"amount":[2],"of":[3,23,96,210,231,238],"information":[4],"on":[5,213],"the":[6,15,33,46,50,60,79,86,129,133,146,167,177,182,208],"Web":[7,37,48,62,92,119,140,152,184,217,241],"today":[8],"is":[9,94,142,157],"available":[10],"only":[11,134],"through":[12],"search":[13,27,64],"interfaces:":[14],"users":[16],"have":[17],"to":[18,31,44,59,83,105,137,155,159,164,166,175],"type":[19],"in":[20,25,29,78,202,227],"a":[21,26,138,143,150,172,199,239],"set":[22],"keywords":[24],"form":[28],"order":[30],"access":[32],"pages":[34,40,71,127],"from":[35,128],"certain":[36],"sites.":[38],"These":[39],"are":[41,55,222],"often":[42,95],"referred":[43],"as":[45],"Hidden":[47,61,91,118,130,139,151,183,216,240],"or":[49],"Deep":[51],"Web.":[52,131],"Since":[53,132],"there":[54],"no":[56],"static":[57],"links":[58],"pages,":[63],"engines":[65],"cannot":[66],"discover":[67,124],"and":[68,72,100,125,185,219],"index":[69],"such":[70],"thus":[73],"do":[74],"not":[75],"return":[76],"them":[77],"results.":[80],"However,":[81],"according":[82],"recent":[84],"studies,":[85],"content":[87],"provided":[88],"by":[89],"many":[90,106],"sites":[93,218],"very":[97,223],"high":[98],"quality":[99],"can":[101,114,122],"be":[102],"extremely":[103],"valuable":[104],"users.In":[107],"this":[108],"paper,":[109],"we":[110,113,170,186],"study":[111],"how":[112,158],"build":[115],"an":[116],"effective":[117,188],"crawler":[120,153],"that":[121,149],"autonomously":[123],"download":[126],"\"entry":[135],"point\"":[136],"site":[141,242],"query":[144,178,201],"interface,":[145],"main":[147],"challenge":[148],"has":[154],"face":[156],"automatically":[160],"generate":[161],"meaningful":[162],"queries":[163,192],"issue":[165],"site.":[168],"Here,":[169],"provide":[171],"theoretical":[173],"framework":[174],"investigate":[176],"generation":[179],"problem":[180],"for":[181,190],"propose":[187],"policies":[189,195,212,233],"generating":[191],"automatically.":[193],"Our":[194],"proceed":[196],"iteratively,":[197],"issuing":[198,249],"different":[200],"every":[203],"iteration.":[204],"We":[205],"experimentally":[206],"evaluate":[207],"effectiveness":[209],"these":[211],"4":[214],"real":[215],"our":[220,232],"results":[221],"promising.":[224],"For":[225],"instance,":[226],"one":[228,230],"experiment,":[229],"downloaded":[234],"more":[235],"than":[236,251],"90%":[237],"(that":[243],"contains":[244],"14":[245],"million":[246],"documents)":[247],"after":[248],"fewer":[250],"100":[252],"queries.":[253]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":20},{"year":2013,"cited_by_count":19},{"year":2012,"cited_by_count":17}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
