{"id":"https://openalex.org/W1998674327","doi":"https://doi.org/10.1145/1031453.1031456","title":"A two-phase sampling technique for information extraction from hidden web databases","display_name":"A two-phase sampling technique for information extraction from hidden web databases","publication_year":2004,"publication_date":"2004-11-12","ids":{"openalex":"https://openalex.org/W1998674327","doi":"https://doi.org/10.1145/1031453.1031456","mag":"1998674327"},"language":"en","primary_location":{"id":"doi:10.1145/1031453.1031456","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1031453.1031456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th annual ACM international workshop on Web information and data 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/A5109989136","display_name":"Yih-Ling Hedley","orcid":null},"institutions":[{"id":"https://openalex.org/I73417466","display_name":"Coventry University","ror":"https://ror.org/01tgmhj36","country_code":"GB","type":"education","lineage":["https://openalex.org/I73417466"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Y. L. Hedley","raw_affiliation_strings":["Coventry University","#N#Coventry University#N#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Coventry University","institution_ids":["https://openalex.org/I73417466"]},{"raw_affiliation_string":"#N#Coventry University#N#","institution_ids":["https://openalex.org/I73417466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101605509","display_name":"Muhammad Younas","orcid":"https://orcid.org/0000-0003-4161-7843"},"institutions":[{"id":"https://openalex.org/I73417466","display_name":"Coventry University","ror":"https://ror.org/01tgmhj36","country_code":"GB","type":"education","lineage":["https://openalex.org/I73417466"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"M. Younas","raw_affiliation_strings":["Coventry University","#N#Coventry University#N#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Coventry University","institution_ids":["https://openalex.org/I73417466"]},{"raw_affiliation_string":"#N#Coventry University#N#","institution_ids":["https://openalex.org/I73417466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082060220","display_name":"Anne James","orcid":"https://orcid.org/0000-0001-9274-7803"},"institutions":[{"id":"https://openalex.org/I73417466","display_name":"Coventry University","ror":"https://ror.org/01tgmhj36","country_code":"GB","type":"education","lineage":["https://openalex.org/I73417466"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"A. James","raw_affiliation_strings":["Coventry University","#N#Coventry University#N#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Coventry University","institution_ids":["https://openalex.org/I73417466"]},{"raw_affiliation_string":"#N#Coventry University#N#","institution_ids":["https://openalex.org/I73417466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072614956","display_name":"Mark Sanderson","orcid":"https://orcid.org/0000-0003-0487-9609"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"M. Sanderson","raw_affiliation_strings":["University of Sheffield"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sheffield","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.6537,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.95506636,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9857000112533569,"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":0.9721999764442444,"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":0.8271056413650513},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6533016562461853},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5969692468643188},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5877931118011475},{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.5688109397888184},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.4831632971763611},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.46279051899909973},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.44693973660469055},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43809911608695984},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.43590855598449707},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.43420636653900146},{"id":"https://openalex.org/keywords/deep-web","display_name":"Deep Web","score":0.4188779592514038},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.29424941539764404},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.17916616797447205}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8271056413650513},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6533016562461853},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5969692468643188},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5877931118011475},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.5688109397888184},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4831632971763611},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.46279051899909973},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.44693973660469055},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43809911608695984},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.43590855598449707},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.43420636653900146},{"id":"https://openalex.org/C46721378","wikidata":"https://www.wikidata.org/wiki/Q221989","display_name":"Deep Web","level":3,"score":0.4188779592514038},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.29424941539764404},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.17916616797447205},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1031453.1031456","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1031453.1031456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th annual ACM international workshop on Web information and data management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.63.8510","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.63.8510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dis.shef.ac.uk/mark/cv/publications/papers/my_papers/WIDM2004.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":16,"referenced_works":["https://openalex.org/W1956559956","https://openalex.org/W1973625941","https://openalex.org/W1986828474","https://openalex.org/W2013247697","https://openalex.org/W2058374187","https://openalex.org/W2095105111","https://openalex.org/W2104086170","https://openalex.org/W2107143175","https://openalex.org/W2116341550","https://openalex.org/W2129530648","https://openalex.org/W2150721933","https://openalex.org/W2170188121","https://openalex.org/W2325227998","https://openalex.org/W4285719527","https://openalex.org/W6638444108","https://openalex.org/W6685116542"],"related_works":["https://openalex.org/W1979144454","https://openalex.org/W2069679074","https://openalex.org/W4239898202","https://openalex.org/W1559090489","https://openalex.org/W3116613346","https://openalex.org/W2055154498","https://openalex.org/W2115253914","https://openalex.org/W2316185946","https://openalex.org/W1892772476","https://openalex.org/W2182622516"],"abstract_inverted_index":{"Hidden":[0,114],"Web":[1,24,91,115,128],"databases":[2,63],"maintain":[3],"a":[4,38,55,80,110],"collection":[5],"of":[6,54,83,112],"specialised":[7],"documents,":[8],"which":[9,27],"are":[10,21],"dynamically":[11],"generated":[12,22],"in":[13,67,94,98,127],"response":[14],"to":[15,33,100,104],"users'":[16],"queries.":[17,34,105],"However,":[18],"the":[19,51,58,73,86,95],"documents":[20,53,97],"by":[23],"page":[25,92,129],"templates,":[26],"contain":[28],"information":[29,49,102,125],"that":[30,43,120],"is":[31],"irrelevant":[32,124],"This":[35,77],"paper":[36],"presents":[37],"Two-Phase":[39],"Sampling":[40],"(2PS)":[41],"technique":[42],"detects":[44,90],"templates":[45,93,130],"and":[46,72,131,134],"extracts":[47],"query-related":[48],"from":[50],"sampled":[52,75,96],"database.":[56],"In":[57,85],"first":[59],"phase,":[60,88],"2PS":[61,89,108,121],"queries":[62],"with":[64,136],"terms":[65,133],"contained":[66,126],"their":[68],"search":[69],"interface":[70],"pages":[71],"subsequently":[74],"documents.":[76,84],"process":[78],"retrieves":[79],"required":[81],"number":[82,111],"second":[87],"order":[99],"extract":[101],"relevant":[103],"We":[106],"test":[107],"on":[109],"real-world":[113],"databases.":[116],"Experimental":[117],"results":[118],"demonstrate":[119],"effectively":[122],"eliminates":[123],"generates":[132],"frequencies":[135],"improved":[137],"accuracy.":[138]},"counts_by_year":[{"year":2017,"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"}
