{"id":"https://openalex.org/W2058112041","doi":"https://doi.org/10.1145/1559845.1560001","title":"HDSampler","display_name":"HDSampler","publication_year":2009,"publication_date":"2009-06-29","ids":{"openalex":"https://openalex.org/W2058112041","doi":"https://doi.org/10.1145/1559845.1560001","mag":"2058112041"},"language":"en","primary_location":{"id":"doi:10.1145/1559845.1560001","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1559845.1560001","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2009 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/A5109170661","display_name":"Anirban Maiti","orcid":null},"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":true,"raw_author_name":"Anirban Maiti","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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057802863","display_name":"Arjun Dasgupta","orcid":null},"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":"Arjun Dasgupta","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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100641132","display_name":"Nan Zhang","orcid":"https://orcid.org/0000-0001-9620-5665"},"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, D.C., DC, USA","George Washington University, Washington D.C., DC, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"George Washington University, Washington, D.C., DC, USA","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"George Washington University, Washington D.C., DC, USA#TAB#","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":4,"corresponding_author_ids":["https://openalex.org/A5109170661"],"corresponding_institution_ids":["https://openalex.org/I189196454"],"apc_list":null,"apc_paid":null,"fwci":2.2209,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.91030215,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1131","last_page":"1134"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991000294685364,"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/T11106","display_name":"Data Management and Algorithms","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8191170692443848},{"id":"https://openalex.org/keywords/snapshot","display_name":"Snapshot (computer storage)","score":0.5796476602554321},{"id":"https://openalex.org/keywords/mashup","display_name":"Mashup","score":0.5627554655075073},{"id":"https://openalex.org/keywords/deep-web","display_name":"Deep Web","score":0.5571590065956116},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5441078543663025},{"id":"https://openalex.org/keywords/web-analytics","display_name":"Web analytics","score":0.45861199498176575},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45546114444732666},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.43204936385154724},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.41753703355789185},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.2724851965904236},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.27219080924987793},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.25521621108055115},{"id":"https://openalex.org/keywords/web-intelligence","display_name":"Web intelligence","score":0.16770756244659424}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8191170692443848},{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.5796476602554321},{"id":"https://openalex.org/C196126337","wikidata":"https://www.wikidata.org/wiki/Q821080","display_name":"Mashup","level":4,"score":0.5627554655075073},{"id":"https://openalex.org/C46721378","wikidata":"https://www.wikidata.org/wiki/Q221989","display_name":"Deep Web","level":3,"score":0.5571590065956116},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5441078543663025},{"id":"https://openalex.org/C516187249","wikidata":"https://www.wikidata.org/wiki/Q10719477","display_name":"Web analytics","level":5,"score":0.45861199498176575},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45546114444732666},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.43204936385154724},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.41753703355789185},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.2724851965904236},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.27219080924987793},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.25521621108055115},{"id":"https://openalex.org/C544335954","wikidata":"https://www.wikidata.org/wiki/Q2553348","display_name":"Web intelligence","level":4,"score":0.16770756244659424},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1559845.1560001","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1559845.1560001","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2009 ACM SIGMOD International Conference on Management of data","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":2,"referenced_works":["https://openalex.org/W2102815161","https://openalex.org/W2129817180"],"related_works":["https://openalex.org/W2154270547","https://openalex.org/W3002405669","https://openalex.org/W66507862","https://openalex.org/W2341203197","https://openalex.org/W2112107765","https://openalex.org/W1982802095","https://openalex.org/W1851202668","https://openalex.org/W87798777","https://openalex.org/W2377354346","https://openalex.org/W4386599833"],"abstract_inverted_index":{"A":[0],"large":[1],"number":[2],"of":[3,26,42,55,73,79,98,110,117,139,143,146,152],"online":[4],"databases":[5,32,75],"are":[6],"hidden":[7,31,66,125],"behind":[8],"the":[9,27,38,53,59,74,108,134,140],"web.":[10],"Users":[11],"to":[12,21,52,82],"these":[13],"systems":[14],"can":[15],"form":[16],"queries":[17],"through":[18],"web":[19,67,126],"forms":[20],"retrieve":[22],"a":[23,96,123,137,150],"small":[24],"sample":[25],"database.":[28],"Sampling":[29],"such":[30,101],"is":[33,58],"widely":[34],"desired":[35],"for":[36,63,88],"understanding":[37],"nature":[39],"and":[40,76,104],"quality":[41],"data":[43,89],"stored":[44],"in":[45,149],"them.":[46],"We":[47],"have":[48],"developed":[49],"HDSampler,":[50,133],"which":[51],"best":[54],"our":[56],"knowledge":[57],"first":[60],"practical":[61],"system":[62],"sampling":[64,72],"structured":[65],"databases.":[68],"It":[69],"enables":[70],"efficient":[71],"accurate":[77],"answering":[78],"aggregate":[80],"queries,":[81],"provide":[83],"analysts":[84],"with":[85],"valuable":[86],"information":[87],"analytics,":[90],"as":[91,93,102],"well":[92],"help":[94],"power":[95],"multitude":[97],"third-party":[99],"applications":[100],"web-mashups":[103],"meta-search":[105],"engines.":[106],"For":[107],"purpose":[109],"this":[111],"demo,":[112],"we":[113],"present":[114],"an":[115],"instance":[116],"HDSampler":[118],"on":[119],"Google":[120,147],"Base":[121,148],"-":[122],"content-rich":[124],"database":[127],"maintained":[128],"by":[129],"Google.":[130],"By":[131],"using":[132],"demo":[135],"reveals":[136],"snapshot":[138],"marginal":[141],"distribution":[142],"various":[144],"attributes":[145],"matter":[151],"minutes.":[153]},"counts_by_year":[{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}
