{"id":"https://openalex.org/W2028574166","doi":"https://doi.org/10.1145/1989323.1989381","title":"Attribute domain discovery for hidden web databases","display_name":"Attribute domain discovery for hidden web databases","publication_year":2011,"publication_date":"2011-06-12","ids":{"openalex":"https://openalex.org/W2028574166","doi":"https://doi.org/10.1145/1989323.1989381","mag":"2028574166"},"language":"en","primary_location":{"id":"doi:10.1145/1989323.1989381","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1989323.1989381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 ACM SIGMOD International Conference on Management of data","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/A5101882004","display_name":"Xin Jin","orcid":"https://orcid.org/0000-0001-8741-5847"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xin Jin","raw_affiliation_strings":["George Washington University, Washington, DC, USA"],"affiliations":[{"raw_affiliation_string":"George Washington University, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103883353","display_name":"Nan Zhang","orcid":"https://orcid.org/0009-0001-1836-7332"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nan Zhang","raw_affiliation_strings":["George Washington University, Washington , DC, USA"],"affiliations":[{"raw_affiliation_string":"George Washington University, Washington , DC, USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002203026","display_name":"Gautam Das","orcid":"https://orcid.org/0000-0002-4627-9065"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gautam Das","raw_affiliation_strings":["University of Texas at Arlington, Arlington, TX, USA","[University of Texas at Arlington, Arlington, TX, USA]"],"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]},{"raw_affiliation_string":"[University of Texas at Arlington, Arlington, TX, USA]","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101882004"],"corresponding_institution_ids":["https://openalex.org/I193531525"],"apc_list":null,"apc_paid":null,"fwci":9.6065,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.97581694,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"553","last_page":"564"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9900000095367432,"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/T11719","display_name":"Data Quality and Management","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7971376776695251},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6218111515045166},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5088179707527161},{"id":"https://openalex.org/keywords/deep-web","display_name":"Deep Web","score":0.4995145797729492},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.46514689922332764},{"id":"https://openalex.org/keywords/database-schema","display_name":"Database schema","score":0.4234687387943268},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.41966909170150757},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3710656464099884},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36525392532348633},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2923460602760315},{"id":"https://openalex.org/keywords/database-design","display_name":"Database design","score":0.27705657482147217},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.19114580750465393},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06979969143867493}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7971376776695251},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6218111515045166},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5088179707527161},{"id":"https://openalex.org/C46721378","wikidata":"https://www.wikidata.org/wiki/Q221989","display_name":"Deep Web","level":3,"score":0.4995145797729492},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.46514689922332764},{"id":"https://openalex.org/C30775581","wikidata":"https://www.wikidata.org/wiki/Q632285","display_name":"Database schema","level":3,"score":0.4234687387943268},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.41966909170150757},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3710656464099884},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36525392532348633},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2923460602760315},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.27705657482147217},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.19114580750465393},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06979969143867493},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1989323.1989381","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1989323.1989381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1605217017","https://openalex.org/W1970173714","https://openalex.org/W1985079777","https://openalex.org/W1986828474","https://openalex.org/W2003316857","https://openalex.org/W2015432483","https://openalex.org/W2018816493","https://openalex.org/W2022760666","https://openalex.org/W2027780984","https://openalex.org/W2041771431","https://openalex.org/W2060088491","https://openalex.org/W2102815161","https://openalex.org/W2108489852","https://openalex.org/W2123853152","https://openalex.org/W2125638313","https://openalex.org/W2129817180","https://openalex.org/W2131006463","https://openalex.org/W2131552526","https://openalex.org/W2136059419","https://openalex.org/W2139259611","https://openalex.org/W2164520297","https://openalex.org/W2170188121","https://openalex.org/W4206551437","https://openalex.org/W6685116542","https://openalex.org/W6902931378"],"related_works":["https://openalex.org/W2037906003","https://openalex.org/W4378699829","https://openalex.org/W2953265498","https://openalex.org/W2533455610","https://openalex.org/W4248236804","https://openalex.org/W2910532728","https://openalex.org/W2963068115","https://openalex.org/W2028002993","https://openalex.org/W2894093432","https://openalex.org/W4375928480"],"abstract_inverted_index":{"Many":[0],"web":[1,67],"databases":[2],"are":[3,23],"hidden":[4,49,63],"behind":[5],"restrictive":[6],"form-like":[7],"interfaces":[8],"which":[9,96],"may":[10,12],"or":[11],"not":[13,24],"provide":[14,97],"domain":[15,26,59,80,104],"information":[16],"for":[17,72],"an":[18,76],"attribute.":[19],"When":[20],"attribute":[21],"domains":[22],"available,":[25],"discovery":[27,60,81],"becomes":[28],"a":[29,36,62],"critical":[30],"challenge":[31],"facing":[32],"the":[33,56,88,101,115],"application":[34],"of":[35,39,58,103,117],"broad":[37],"range":[38],"existing":[40],"techniques":[41,95],"on":[42,79,100],"third-party":[43],"analytical":[44],"and":[45,110],"mash-up":[46],"applications":[47],"over":[48,61],"databases.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54],"consider":[55],"problem":[57],"database":[64,74],"through":[65],"its":[66],"interface.":[68],"We":[69,91,106],"prove":[70],"that":[71],"any":[73],"schema,":[75],"achievability":[77],"guarantee":[78],"can":[82],"be":[83],"made":[84],"based":[85],"solely":[86],"upon":[87],"interface":[89],"design.":[90],"also":[92],"develop":[93],"novel":[94],"effective":[98],"guarantees":[99],"comprehensiveness":[102],"discovery.":[105],"present":[107],"theoretical":[108],"analysis":[109],"extensive":[111],"experiments":[112],"to":[113],"illustrate":[114],"effectiveness":[116],"our":[118],"approach.":[119]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
