{"id":"https://openalex.org/W4247901641","doi":"https://doi.org/10.1109/asonam.2014.6921664","title":"Estimating the size of hidden data sources by queries","display_name":"Estimating the size of hidden data sources by queries","publication_year":2014,"publication_date":"2014-08-01","ids":{"openalex":"https://openalex.org/W4247901641","doi":"https://doi.org/10.1109/asonam.2014.6921664"},"language":"en","primary_location":{"id":"doi:10.1109/asonam.2014.6921664","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asonam.2014.6921664","pdf_url":null,"source":{"id":"https://openalex.org/S4363608209","display_name":"2014 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2014)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2014)","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/A5100322854","display_name":"Yan Wang","orcid":"https://orcid.org/0000-0002-9876-5823"},"institutions":[{"id":"https://openalex.org/I137867983","display_name":"Central University of Finance and Economics","ror":"https://ror.org/008e3hf02","country_code":"CN","type":"education","lineage":["https://openalex.org/I137867983"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yan Wang","raw_affiliation_strings":["School of Information, Central University of Finance and Economics, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information, Central University of Finance and Economics, Beijing, China","institution_ids":["https://openalex.org/I137867983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108166775","display_name":"Jie Liang","orcid":"https://orcid.org/0000-0003-3003-4343"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Liang","raw_affiliation_strings":["BiblioCommons Inc., Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"BiblioCommons Inc., Toronto, Canada","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100811291","display_name":"Jianguo L\u00fc","orcid":null},"institutions":[{"id":"https://openalex.org/I74413500","display_name":"University of Windsor","ror":"https://ror.org/01gw3d370","country_code":"CA","type":"education","lineage":["https://openalex.org/I74413500"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jianguo Lu","raw_affiliation_strings":["School of Computer Science, University of Windsor, Windsor, Canada"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Windsor, Windsor, Canada","institution_ids":["https://openalex.org/I74413500"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100322854"],"corresponding_institution_ids":["https://openalex.org/I137867983"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58538404,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"18","issue":null,"first_page":"712","last_page":"719"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9987999796867371,"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":0.9987999796867371,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9869999885559082,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9846000075340271,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8156986236572266},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.735960841178894},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.502253532409668},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.49968814849853516},{"id":"https://openalex.org/keywords/competitor-analysis","display_name":"Competitor analysis","score":0.47843292355537415},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4600318670272827},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.44521433115005493},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33727964758872986},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22808495163917542}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8156986236572266},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.735960841178894},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.502253532409668},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.49968814849853516},{"id":"https://openalex.org/C127576917","wikidata":"https://www.wikidata.org/wiki/Q624630","display_name":"Competitor analysis","level":2,"score":0.47843292355537415},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4600318670272827},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.44521433115005493},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33727964758872986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22808495163917542},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asonam.2014.6921664","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asonam.2014.6921664","pdf_url":null,"source":{"id":"https://openalex.org/S4363608209","display_name":"2014 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2014)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2014)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1605217017","https://openalex.org/W1617966546","https://openalex.org/W1970173714","https://openalex.org/W1983416950","https://openalex.org/W2013970953","https://openalex.org/W2019491306","https://openalex.org/W2026289298","https://openalex.org/W2028716813","https://openalex.org/W2041258965","https://openalex.org/W2047836387","https://openalex.org/W2081948558","https://openalex.org/W2089657469","https://openalex.org/W2094930182","https://openalex.org/W2120642948","https://openalex.org/W2121315872","https://openalex.org/W2123159709","https://openalex.org/W2128941908","https://openalex.org/W2136059419","https://openalex.org/W2147164982","https://openalex.org/W2148738951","https://openalex.org/W2154707336","https://openalex.org/W4241604826","https://openalex.org/W6636631317","https://openalex.org/W6677778574"],"related_works":["https://openalex.org/W2358804928","https://openalex.org/W4225710828","https://openalex.org/W1998528887","https://openalex.org/W2965538880","https://openalex.org/W2143282039","https://openalex.org/W2528370785","https://openalex.org/W4200335562","https://openalex.org/W2861933770","https://openalex.org/W2361145238","https://openalex.org/W2371267447"],"abstract_inverted_index":{"The":[0],"sizes":[1],"of":[2,7,20,58,62,88,102,115],"hidden":[3,21],"data":[4,22,91],"sources":[5,23],"are":[6,32],"great":[8],"interests":[9],"to":[10,54,76],"public,":[11],"researchers":[12],"and":[13,119,126],"even":[14],"business":[15],"competitors.":[16],"Estimating":[17],"the":[18,35,55,59,65,78,89,103,121,127,135],"size":[19],"has":[24],"been":[25],"a":[26,44,73,82,86,113],"challenging":[27],"problem.":[28],"Most":[29],"existing":[30],"methods":[31],"derived":[33],"from":[34,85],"classic":[36],"capture-recapture":[37],"methods.":[38],"Another":[39],"approach":[40],"is":[41,50,98,110],"based":[42],"on":[43,112,133],"large":[45,56,116],"query":[46,66,83,124],"pool.":[47,67],"This":[48],"method":[49,75,109,125,132],"not":[51],"accurate":[52],"due":[53],"variance":[57,79,97],"document":[60,95],"frequencies":[61],"queries":[63],"in":[64],"Targeting":[68],"this":[69],"problem,":[70],"we":[71],"propose":[72],"new":[74],"reduce":[77],"by":[80],"constructing":[81],"pool":[84],"sample":[87],"target":[90],"source":[92],"so":[93],"that":[94],"frequency":[96],"reduced,":[99],"yet":[100],"most":[101],"documents":[104],"can":[105],"be":[106],"covered.":[107],"Our":[108],"tested":[111],"variety":[114],"textual":[117],"corpora,":[118],"outperforms":[120],"baseline":[122],"random":[123],"Broder":[128],"et":[129],"al's":[130],"estimation":[131],"all":[134],"datasets.":[136]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}